INDEX

Explanations

code, media, and services

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

 registro

-0.76

英雄

-0.72

Ratio

-0.71

ULAN

-0.69

 Algeria

-0.69

 undisputed

-0.68

貸

-0.68

 Acknowledge

-0.68

 Ratio

-0.68

 somit

-0.68

POSITIVE LOGITS

accumulator

0.81

蟎

0.78

Nen

0.77

 Morel

0.77

orient

0.76

nių

0.75

 Mule

0.75

ครับ

0.75

tored

0.73

 DataLoader

0.71

Activations Density 0.003%