INDEX

Explanations

university names

The neuron activates on numeric tokens—especially decimal numbers—throughout the text.

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

 erneu

-1.76

-1.73

泐

-1.71

ículos

-1.65

亹

-1.62

 दोनों

-1.52

鲧

-1.51

 aktualisiert

-1.51

");

-1.50

brakk

-1.49

POSITIVE LOGITS

you

1.90

is

1.83

 your

1.59

 which

1.57

1.56

⅕

1.55

⅛

1.48

 historiador

1.46

⅝

1.46

 básicos

1.39

Activations Density 0.129%