INDEX

Explanations

Mixed languages, technical content

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Fang

-1.16

Fang

-0.95

isi

-0.85

enderror

-0.64

 fang

-0.57

 BorderSide

-0.56

Isi

-0.56

Isi

-0.54

ponses

-0.52

Weblinks

-0.52

POSITIVE LOGITS

 Wikimedijinoj

0.76

PasswordEncoder

0.62

تقاوى

0.56

 дописавши

0.54

std

0.52

URLConnection

0.51

 Mays

0.51

Искәрмәләр

0.49

 Strict

0.49

Šaltiniai

0.48

Activations Density 0.347%