INDEX

Explanations

command line tools and abbreviations

The neuron fires on tokens containing digits (i.e. numeric strings or alphanumeric sequences with numbers).

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

とき

-1.09

ess

-1.04

ene

-0.95

とともに

-0.95

 serious

-0.93

్య

-0.92

್ಯ

-0.90

اته

-0.89

 моя

-0.82

est

-0.81

POSITIVE LOGITS

رر

1.17

rrrr

1.11

iss

1.03

0.96

̩

0.87

RRRR

0.83

ra

0.82

halter

0.80

ons

0.79

תיים

0.79

Activations Density 0.105%