INDEX

Explanations

code snippets

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 Majefty

-0.73

 fhew

-0.69

^(@)

-0.69

 debout

-0.68

 poffible

-0.68

 näytte

-0.67

 neceff

-0.66

 himſelf

-0.66

 prieten

-0.65

 câte

-0.64

POSITIVE LOGITS

rungsseite

0.49

 remove

0.48

 fitted

0.44

 ORGAN

0.43

 remo

0.42

IContainer

0.41

 organiz

0.41

Organization

0.41

 removed

0.40

 removing

0.40

Activations Density 0.000%

No Known Activations