INDEX

Explanations

average value

self-deprecating humor

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

Ро

0.52

Контак

0.46

рақ

0.46

 त्यांच्या

0.45

рун

0.45

ле

0.44

켄

0.44

ыз

0.44

ந்தார்

0.43

 кино

0.43

POSITIVE LOGITS

 forestry

0.44

 negligible

0.42

batross

0.41

av

0.40

!!!!!!!!

0.40

 biotic

0.40

rying

0.40

 راستہ

0.40

 可以

0.39

海

0.38

Activations Density 0.001%