INDEX

Explanations

mathematical division

The neuron selectively activates on numeric tokens (multi‐digit and decimal numbers) in 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

久し

-1.93

さぁ

-1.77

あぁ

-1.63

niño

-1.59

マジで

-1.57

もうすぐ

-1.56

久しぶりに

-1.55

❢

-1.55

ほうがいい

-1.55

XDD

-1.54

POSITIVE LOGITS

GRAFÍA

1.79

1.78

—

1.52

 Grüßen

1.47

to

1.45

déric

1.41

 they

1.35

get

1.30

all

1.30

Activations Density 0.042%