Skip to content
mini-lab
Features of prelude-2

Feature #773

Fires on “Once” (not labeled yet: read the examples)

Fires on
0.29% of tokens
Mostly in
story
Layer
after block 4

Where it fires

  • story 74%
  • chat 21%
  • agent 4%
  • python 0%
  • worksheet 0%

Makes the model say

day playing fast happy nextbye equals README

Makes it not say

only divisibletools tests himself": wse

Strongest examples

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

  1. story 4.26
    : hello.py<|tool_end|><|assistant_start|>Created `hello.py`.<|assistant_end|><|bos|>Once upon a time,
  2. story 4.13
    <|assistant_start|>The answer is 86.<|assistant_end|><|bos|>Once upon a time,
  3. story 4.09
    greeting.py<|tool_end|><|assistant_start|>Created `greeting.py`.<|assistant_end|><|bos|>Once upon a time,
  4. story 4.04
    stats.py` with `keep_even(nums)`.<|assistant_end|><|bos|>Once upon a time there
  5. story 4.03
    stats.py` with `max_item(nums)`.<|assistant_end|><|bos|>Once upon a time,
  6. story 4.02
    Added `total(nums)` to `utils.py`.<|assistant_end|><|bos|>Once upon a time,
  7. story 3.99
    py`.<|assistant_end|><|bos|>Once upon a time,
  8. story 3.97
    They played all day and enjoyed being friends in the sea.<|assistant_end|><|bos|>Once upon a time,
  9. story 3.96
    <|think_end|>The answer is 32.<|assistant_end|><|bos|>Once upon a time,
  10. story 3.96
    model: I can only tell short stories and add numbers.<|assistant_end|><|bos|>Once upon a time,
  11. story 3.94
    Created `utils.py` with `largest(nums)`.<|assistant_end|><|bos|>Once upon a time,
  12. story 3.94
    61<|tool_end|><|assistant_start|>The answer is 261.<|assistant_end|><|bos|>Once upon a time there