INDEX

Explanations

. followed by punctuation

The neuron strongly activates on numeric tokens (digits, years, measurements, stats) in the text.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 acondicionado

0.61

 daño

0.59

!_

0.59

ificazione

0.59

￳

0.58

 பாபிலோ

0.58

<unused38>

0.57

'',

0.57

itelji

0.57

 vantaggio

0.57

POSITIVE LOGITS

.,

1.09

0.97

.~

0.95

.:

0.93

٫

0.93

.;

0.92

.,"

0.90

.(\

0.90

.%

0.89

.]+

0.88

Activations Density 0.445%