INDEX

Explanations

parts of words, prefixes, suffixes

This neuron fires on rare or out-of-vocabulary tokens—chiefly unusual proper names or other low-frequency words.

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

ó

0.15

ਸ

0.14

ᴀ

0.14

ِل

0.14

َل

0.13

We

0.13

َه

0.13

ullie

0.13

ologne

0.13

↵

0.13

POSITIVE LOGITS

HBC

0.16

 Mandalorian

0.16

RBD

0.16

 ocas

0.16

 maniera

0.16

getPage

0.16

 Roles

0.15

 Modo

0.15

 Wayback

0.15

 Twilight

0.15

Activations Density 0.002%