INDEX

Explanations

ranks followed by numbers

The neuron is primarily triggered by standalone numeric tokens (especially multi‐digit 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

 only

-1.44

 often

-1.23

any

-1.20

 with

-1.15

 have

-1.13

 since

-1.13

 making

-1.11

so

-1.10

 Since

-1.07

by

-1.04

POSITIVE LOGITS

Drupal

0.88

ſelf

0.88

Numerade

0.85

 رغم

0.85

 évalu

0.85

 Jacobson

0.85

こない

0.83

 acht

0.83

 caractères

0.82

 enlarging

0.82

Activations Density 0.006%