INDEX

Explanations

any followed by category

The neuron strongly activates on the indefinite quantifier “any.”

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 lorsqu

-1.73

 БО

-1.65

In

-1.65

椟

-1.60



-1.58

 powiedzieć

-1.48

……”

-1.48

𓆉

-1.45

𓁹

-1.43

 occuper

-1.41

POSITIVE LOGITS

of

2.55

 else

1.74

1.69

 heutige

1.57

 other

1.34

 ehemalige

1.30

We

1.30

 bekannte

1.29

 there

1.27

 bezeich

1.27

Activations Density 0.037%