Pharmacoencephalography (pharmaco-EEG) is a prominent instrument for the pharmacological screening of new psychoactive molecules. This experimental approach has not remained a vestige of neurobiological studies, and can be used successfully to complete today's research objectives. The development and rise to universal use of machine learning techniques opens up novel prospects for the use of pharmaco-EEG data to solve the problems of classification and prognosis. We have previously shown that naive Bayes classifier (NBC) combined with principal component analysis (PCA) can be used to differentiate between antipsychotic and sedative drug effects as well as to distinguish among the antipsychotics' effects. In the present study, we evaluated the possibility to employ this method to assess the dose-dependency of antipsychotic effects. The experiments were carried out in white outbred male rats with chronically implanted electrocorticographic electrodes. As the agents of interest, we chose two drugs with antipsychotic activity, chlorpromazine and promethazine, in three doses each (0.1, 1, 10 mg/kg and 0.5, 5 and 20 mg/kg, respectively). The training set, used as a reference to determine the pharmacological effects of the agents of interest, included the D-2-dopamine receptor blocker haloperidol, M-cholinergic receptor blocker tropicamide, H-1-histamine receptor blocker chloropyramine, the sedative dexmedetomidine, and the anxiolytic phenazepam. We have shown that the lowest chlorpromazine dose (0.1 mg/kg) can be characterized as antipsychotic with a marked histaminolytic effect, while the highest one (10 mg/kg) exhibits predominantly antipsychotic activity with a cataleptogenic effect. All three doses demonstrated anticholinergic activity, which increased with the dose. For promethazine, we observed a clear dose-dependent shift from antipsychotic action to cataleptogenic, alongside a notable antimuscarinic effect of all doses. None of promethazine doses showed any resemblance to chloropyramine, which probably indicates its anti-dopaminergic and antimuscarinic effects being able to mask its H1-antihistamine effect in the used dose range. In summary, our results demonstrate that NBC combined with PCA can be used to determine the dose-dependency of antipsychotic agents' effects based on their impact on electrocorticogram parameters. Further development of this method as well as expansion of psychotropic agent electropharmacogram library would allow for more precise prediction of pharmacological activity of the agents of interest.