INDEX

Explanations

introduction and sections

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 baku

-0.77

zungs

-0.77

 mawar

-0.76

nette

-0.75

 kafe

-0.74

ガル

-0.71

образ

-0.71

 cérami

-0.71

enak

-0.71

cznych

-0.70

POSITIVE LOGITS

multer

0.99

fieldname

0.95

 multer

0.93

ΑΙ

0.91

 dest

0.87

mimetype

0.86

Ճ

0.86

 dichotomy

0.84

kien

0.83

 lesbians

0.83

Activations Density 0.002%