My intuition is opposite - that conscious thought is primarily from sparse activations roughly corresponding to distinct concepts that basically get looked up through learned associations with other such concepts (symbolic reasoning-like). I'm imagining the RNN "strong conceptual embeddings" as fairly dense and opaque, which I would more think of as unconscious or intuitive.
@yacineMTB@HSVSphere I personally feel like these fake emotional responses should be purged from the models. They should be quite easy to detect in RL I would think.