INDEX

Explanations

Explained

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 صفحات

-0.53

 Levin

-0.50

Big

-0.49

 dist

-0.48

vir

-0.48

Walking

-0.48

Distance

-0.47

й

-0.47

und

-0.47

 Walking

-0.47

POSITIVE LOGITS

 ſtand

0.85

 myſelf

0.76

 raiſ

0.75

 BoxFit

0.74

complexContent

0.72

 tranſ

0.72

jsxFileName

0.71

 houſe

0.68

 deſt

0.68

 pleaſure

0.68

Activations Density 0.048%