INDEX

Explanations

license text or code header

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

後的

-0.77

vis

-0.76

Ign

-0.74

 Ausführungen

-0.73

ugas

-0.69

̍

-0.68

 tertentu

-0.68

ranza

-0.68

グロ

-0.66

karan

-0.66

POSITIVE LOGITS

 including

1.06

0.97

including

0.91

 Including

0.89

ళ్

0.85

 cercana

0.81

Including

0.81

 INCLUDING

0.80

ու

0.79

decrypted

0.78

Activations Density 0.054%