INDEX

Explanations

BIT followed by numbers

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

 preparar

-0.79

{}{}

-0.75

 painless

-0.73

raisals

-0.71

 preparation

-0.70

ároz

-0.69

 préparation

-0.68

blems

-0.68

 cera

-0.68

zwi

-0.67

POSITIVE LOGITS

 segíts

0.80

 hét

0.77

enton

0.77

поги

0.77

ád

0.75

Clo

0.73

ботинки

0.73

NING

0.73

 içerisinde

0.72

itis

0.71

Activations Density 0.045%