Feature #2280

Strongest examples

On text the dictionary never trained on. The underlined token is where it fires most.

1. story 11.5
   <|bos|>Anna loved animals. She
2. story 10.58
   <|assistant_end|><|bos|>Lily loves to dance.
3. worksheet 10.3
   154<|assistant_end|><|bos|>Tom has 24
4. worksheet 10.08
   <|assistant_end|><|bos|>Tom has 87
5. story 9.76
   37 = 91540<|bos|>Tom and Mia were best
6. story 9.37
   items)`. The tests pass now.<|assistant_end|><|bos|>Lily and Ben are playing
7. story 8.96
   model: I can only tell short stories and add numbers.<|assistant_end|><|bos|>Lily and Ben were playing
8. story 8.81
   (nums)` returns every number of nums doubled.<|assistant_end|><|bos|>Tom and Lily went to
9. story 8.81
   ELLO⏎```<|assistant_end|><|bos|>Lily loved to dance.
10. story 8.74
    552<|think_end|>The answer is 552.<|assistant_end|><|bos|>Lily was a green bird
11. story 8.73
    `last_letter(s)`.<|assistant_end|><|bos|>Tim and Liz liked
12. story 8.73
    in `main.py`.<|assistant_end|><|bos|>Lily and Ben are playing