INDEX

Explanations

children

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 self

-0.52

 small

-0.50

lavi

-0.49

 suro

-0.48

 Dumont

-0.47

FileDescriptor

-0.47

ed

-0.46

хай

-0.45

 Small

-0.45

en

-0.44

POSITIVE LOGITS

 CreateTagHelper

0.85

 препратки

0.79

niająca

0.71

astéroïdes

0.71

 Infórmanos

0.70

.”)

0.68

 Италијани

0.67

tamment

0.66

Читати

0.65

TagMode

0.65

Activations Density 0.100%