INDEX

Explanations

The neuron fires strongly on numerical or measurement tokens—especially decimal numbers, distances, and unit-style expressions.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elessly

0.84

esan

0.80

idding

0.73

家

0.73

ristmas

0.71

ロジー

0.70

ます

0.70

 cancer

0.68

rą

0.68

POSITIVE LOGITS

 mevcut

0.84

kör

0.77

အ

0.76

멧

0.71

Τ

0.71

셜

0.71

Duc

0.71

 oficiais

0.70

 Aceh

0.70

Grady

0.70

Activations Density 0.000%