INDEX

Explanations

archives and documents

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

큰

-0.84

後日

-0.79

 avenge

-0.74

ewear

-0.73

样

-0.72

ersachsen

-0.71

طح

-0.71

Olga

-0.71

戦う

-0.71

 творо

-0.71

POSITIVE LOGITS

 archives

2.28

 Archives

1.84

 archival

1.83

 archive

1.77

archives

1.59

 Archive

1.52

Archives

1.49

 documents

1.48

 Archivo

1.45

Archive

1.41

Activations Density 0.015%