INDEX

Explanations

Code/technical language

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

 saites

-0.84

 дописавши

-0.76

Tembelea

-0.72

 ujednoznacz

-0.71

ázaro

-0.69

 XCTest

-0.66

 Dummies

-0.65

ViewStyle

-0.65

///</

-0.64

 Ilya

-0.63

POSITIVE LOGITS

脚注の使い方

0.47

ⓧ

0.41

ParallelGroup

0.40

AndEndTag

0.36

WriteLiteral

0.35

мак

0.34

 Catawiki

0.34

رق

0.34

 Wikispecies

0.33

الإنجليزية

0.31

Activations Density 0.004%