INDEX

Explanations

code comments and licenses

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

 diseases

-0.73

seats

-0.72

diseases

-0.72

に触

-0.71

ビール

-0.69

findViewById

-0.69

'|

-0.69

̾

-0.68

 Diseases

-0.67

 Besoin

-0.67

POSITIVE LOGITS

 Outlook

0.77

 назна

0.68

Fix

0.68

mannian

0.66

color

0.65

 uterine

0.65

مني

0.64

껍

0.63

Fix

0.63

Terra

0.63

Activations Density 0.068%