Skip to content
mini-lab
Features of prelude-2

Feature #388

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

Fires on
1.33% of tokens
Mostly in
agent
Layer
after block 4

Where it fires

  • agent 67%
  • python 28%
  • story 4%
  • chat 1%
  • worksheet 0%

Makes the model say

illpositiveheadletterlespathk(

Makes it not say

_One:txt Tom reallyie divisible

Strongest examples

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

  1. python 6.59
    count_vowels(s):⏎
  2. agent 5.83
    8: ⏎9: def raise_to(a, b
  3. agent 5.79
    5: def first_letter(s):⏎
  4. python 5.61
    ⏎from arith import sum_up_to, lower_of
  5. agent 5.56
    , lines 1-2⏎1: def raise_to(a, b
  6. agent 5.55
    5: ⏎6: ⏎7: def raise_to(a, b
  7. agent 5.46
    from text import final_letter, size⏎2
  8. agent 5.39
    ⏎1: def num_chars(s):⏎
  9. python 5.27
    !"⏎⏎`num_chars(s)` returns
  10. python 5.17
    import first_letter⏎⏎LIMIT =
  11. agent 5.17
    function raise_to that returns a to
  12. python 5.16
    x⏎ return x⏎⏎⏎def sum_up_to(n):⏎