Skip to content
mini-lab
Features of prelude-2

Feature #2154

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

Fires on
2.24% of tokens
Mostly in
python
Layer
after block 4

Where it fires

  • python 79%
  • agent 19%
  • story 1%
  • worksheet 1%
  • chat 0%

Makes the model say

ful happeneditems **owed tests opened[::-

Makes it not say

one example a is F willce far

Strongest examples

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

  1. agent 5.29
    = return b⏎⏎⏎def positive(x):⏎ return x > 0<|tool_call_end|><|assistant_end|>
  2. python 5.11
    ⏎ return x in items⏎⏎⏎def biggest(nums):⏎ return max(nums)⏎
  3. agent 5.1
    ):⏎ return s⏎⏎⏎def initial(s):⏎ return s[0]<|tool_call_end|><|assistant_end|>
  4. python 5.08
    i⏎ return acc⏎⏎⏎def positive(x):⏎ return x > 0⏎⏎
  5. python 4.95
    s[0]⏎⏎⏎def positive(x):⏎ return x > 0⏎⏎⏎
  6. agent 4.91
    items)⏎⏎⏎def sum_list(nums):⏎ result = 0⏎ for n
  7. python 4.83
    1⏎ return k⏎⏎⏎def initial(s):⏎ return s[0]⏎⏎
  8. python 4.83
    * x⏎⏎⏎def is_positive(x):⏎ return x > 0⏎⏎
  9. python 4.78
    `.⏎⏎```python⏎def total(nums):⏎ result = 0⏎ for n
  10. python 4.77
    s)⏎⏎⏎def first_letter(s):⏎ return s[0]⏎⏎
  11. python 4.76
    nums]⏎⏎⏎def contains(items, x):⏎ return x in items⏎⏎⏎def
  12. python 4.75
    nums)⏎⏎⏎def contains(items, x):⏎ return x in items⏎⏎#