Skip to content
mini-lab
Features of prelude-2

Feature #563

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

Fires on
0.19% of tokens
Mostly in
agent
Layer
after block 4

Where it fires

  • agent 41%
  • python 40%
  • story 15%
  • chat 4%
  • worksheet 0%

Makes the model say

to time(,"!",⏎ ver

Makes it not say

old loud at shiny dirty plan evenDon

Strongest examples

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

  1. story 4.46
    ?"⏎Ben smiled and said, "Of course we can. But next time, let's
  2. story 4.35
    okay. We can still make cocoa. Just be more quiet next time." They made
  3. python 4.23
    ⏎⏎>>> positive(6)⏎True⏎⏎```python⏎def factorial(n):
  4. story 4.21
    She was not mad. She told Tim that it was okay, but next time, he should
  5. story 4.11
    . You are too little. The show is for big kids. Maybe next year." Mom said
  6. python 4.06
    TIGER")` returns `"tiger"`.⏎⏎```python⏎def sum_up_
  7. python 4.03
    , 3])⏎4.75⏎⏎```python⏎def excite(s):
  8. python 3.98
    , 4, 2])⏎4⏎<|bos|>```python⏎def odd(x):
  9. python 3.96
    ⏎⏎>>> vowels("lemon")⏎2⏎⏎```python⏎def divides(a,
  10. python 3.91
    >>> is_odd(1)⏎True⏎⏎```python⏎def double(x):
  11. chat 3.91
    But you can learn from this experience and be more careful next time."⏎Lucy
  12. python 3.91
    5])⏎[8, 8]⏎⏎```python⏎def last(items):