Yes, both the output should be "milestones" of sorts, like lemmas and theorems in math. Important plateaus that serve as a launching pad to the next phase. Regurgitating every thought potentially degrades signal:noise ratio.
The hidden states of the tokens likely contain more semantic information than can be extracted by the final projection into token space.
The hidden states of the tokens likely contain more semantic information than can be extracted by the final projection into token space.