What is the formal statement of the fact that logits add for perfectly calibrated and maximally independent predictions?
atticusw
Karma: 17
What is the formal statement of the fact that logits add for perfectly calibrated and maximally independent predictions?
In figure 3, given that 64-shot Haiku does a lot worse than 64-shot Llama 405B-base, should I conclude that base models (without the assistant persona) are way better at generating realistic user prompts?