Skip to content
mini-lab
Features of prelude-2

Feature #17

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

Fires on
1.98% of tokens
Mostly in
python
Layer
after block 4

Where it fires

  • python 44%
  • agent 30%
  • story 15%
  • chat 6%
  • worksheet 5%

Makes the model say

_(!"return smiled return(" heard

Makes it not say

addsnder For foodNo]`.hingnums

Strongest examples

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

  1. python 2.9
    ```python⏎def mean(a, b
  2. python 2.73
    ⏎def exclaim(s):⏎ return s + "!"⏎⏎⏎def add_one(x
  3. python 2.69
    `result = result + 1`.⏎⏎```python⏎def add_all(nums
  4. agent 2.67
    a, b):⏎ return a + b⏎⏎⏎def mean(a, b
  5. python 2.66
    7)` returns `-3`.⏎⏎```python⏎def only_even(nums
  6. python 2.65
    to x.⏎⏎```python⏎def add_one(x
  7. python 2.64
    x % 2 == 1`.⏎⏎```python⏎def even(x):⏎
  8. python 2.62
    6])` returns `6`.⏎⏎```python⏎def mean(a, b
  9. python 2.61
    ])` returns `4`.⏎⏎```python⏎def only_even(nums
  10. python 2.54
    x % 3 == 0`.⏎⏎```python⏎def even(x):⏎
  11. python 2.54
    s`.⏎⏎```python⏎def loud(s):⏎
  12. python 2.54
    ` with `return a ** b`.⏎⏎```python⏎def raise_to(a