INDEX

Explanations

reviews and ratings

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

 rating

-0.76

 ratings

-0.75

 Ratings

-0.65

 Rating

-0.61

ratings

-0.60

rating

-0.59

 rated

-0.53

Ratings

-0.52

Rating

-0.50

 RATING

-0.49

POSITIVE LOGITS

 purpoſe

0.75

Бахар

0.70

pañas

0.69

DebuggerNonUser

0.67

 RSSSF

0.66

 odkazy

0.66

 Anſ

0.65

 uſed

0.65

 juſt

0.65

 neceff

0.63

Activations Density 0.037%