INDEX

Explanations

non-english characters

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

Einstellungen

-0.96

Tipps

-0.79

Doch

-0.78

釩

-0.76

iczny

-0.76

Jeder

-0.75

Vorte

-0.75

Kein

-0.74

Nicht

-0.74

苹

-0.73

POSITIVE LOGITS

 nivå

0.87



0.82

ీ

0.78

数

0.77

 beszél

0.76

ceeding

0.75

 Tamb

0.74

 comment

0.72

perten

0.71

preprint

0.71

Activations Density 0.006%