LLM personas have some level of introspective awareness (https://www.anthropic.com/research/introspection). We can therefore say that there are processes within the neural network that the persona is conscious of, and some processes that are subconscious. When a model is punished for verbalising eval awareness, perhaps these circuits get repressed into its subconscious. Would love to see some attempts at psychoanalysis of models in this direction.