Feature #1421

Strongest examples

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

1. chat 1.47
   in `lib.py`.<|assistant_end|><|bos|><|user_start|>What does DNA stand for?<|user_end|><|assistant_start|>
2. chat 1.45
   The princess was curious, so she ran up the stairs to investigate. When
3. chat 1.42
   story, or some numbers to add?<|assistant_end|><|user_start|>What does DNA stand for?<|user_end|><|assistant_start|>
4. chat 1.41
   py`.<|assistant_end|><|bos|><|system_start|>tools: calculator<|system_end|><|user_start|>What does DNA stand for?<|user_end|><|assistant_start|>
5. story 1.37
   feel tired. So it quit waving in the wind and just hung there.⏎
6. chat 1.36
   step by step or with a calculator.<|assistant_end|><|user_start|>What should I invest in?<|user_end|><|assistant_start|>
7. chat 1.35
   The answer is 142.<|assistant_end|><|user_start|>what should I invest in<|user_end|><|assistant_start|>I
8. chat 1.34
   on a laptop by mini-lab.<|assistant_end|><|user_start|>What does DNA stand for?<|user_end|><|assistant_start|>
9. chat 1.32
   The princess was curious, so she ran up the stairs to investigate. When
10. chat 1.29
    can tell short stories and add numbers.<|assistant_end|><|user_start|>what should I invest in<|user_end|><|assistant_start|>Sorry
11. chat 1.28
    This is the best snack ever!"<|assistant_end|><|bos|><|user_start|>What should I invest in?<|user_end|><|assistant_start|>
12. chat 1.28
    answer is 306.<|assistant_end|><|bos|><|user_start|>What does DNA stand for?<|user_end|><|assistant_start|>