INDEX

Explanations

torch

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

 Glass

-0.51

encer

-0.50

 theo

-0.49

Florence

-0.44

Glass

-0.44

 BARBARA

-0.42

 Bubble

-0.42

floxacin

-0.41

nish

-0.41

 Essen

-0.40

POSITIVE LOGITS

PerformLayout

1.11

UnusedPrivate

0.88

 cherchés

0.83

RTLD

0.79

 дописавши

0.77

ConstraintMaker

0.75

 createContext

0.75

afficheront

0.73

UrlResolution

0.71

Tikang

0.70

Activations Density 0.017%