INDEX

Explanations

foreign language content

personalized stickers

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

고

0.52

 drab

0.44

 रुग्

0.44

怵

0.43

れます

0.43

↵

0.43

bahn

0.42

read

0.42

絡

0.42

rient

0.41

POSITIVE LOGITS

']].

0.52

 harmful

0.52

িপি

0.50

 contento

0.50

agamanam

0.49

ឬ

0.49

াকারী

0.49

</bbox>

0.48

мана

0.48

 השני

0.47

Activations Density 0.001%