Feature #678
Fires on “tiger” (not labeled yet: read the examples)
- Fires on
- 0.63% of tokens
- Mostly in
- python
- Layer
- after block 4
Where it fires
- python 65%
- agent 18%
- story 9%
- worksheet 5%
- chat 3%
Makes the model say
")")`!")])/<|think_end|><|tool_end|> Python
Makes it not say
Butse1 touch, itw tree
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
python 6.04"ROBOT"⏎assert combine("tiger", "tiger") == "tiger
-
python 5.48, first_letter⏎⏎assert join_words("music", "tiger") == "music
-
python 5.45last_letter("apple") == "e"⏎assert vowels("banana") == 3
-
python 5.44a space. For example, `join_words("banana", "tiger")` returns `"banana
-
python 5.37k + 1⏎ return k⏎```⏎⏎>>> vowels("lemon")⏎2⏎
-
python 5.23"⏎assert vowels("hello") == 2⏎assert vowels("banana") == 3
-
python 5.21greetings import count_vowels, hello⏎⏎assert count_vowels("house") == 3
-
python 5.17b with a space. For example, `combine("tiger", "tree")` returns `"tiger
-
python 5.15, length, welcome⏎⏎assert join_words("tiger", "lemon") == "tiger
-
python 5.15b with a space. For example, `combine("apple", "lemon")` returns `"apple
-
python 5.14") == "CLOUD"⏎assert count_vowels("hello") == 2
-
python 5.11.py⏎from strings import vowels, hello⏎⏎assert vowels("music") == 2