INDEX

Explanations

words that suggest a broad scope or universality

words indicating universality or categories

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

all

-1.66

 every

-1.61

every

-1.52

 semua

-1.48

 всех

-1.46

 tutte

-1.41

 todas

-1.41

 toutes

-1.36

EVERY

-1.35

all

-1.34

POSITIVE LOGITS

 समीक्षक

0.75

 kinds

0.68

 types

0.60

FunctionFlags

0.59

Enllaços

0.59

 المعيارى

0.59

 sorts

0.57

ريكية

0.55

 insuffisamment

0.54

 jenis

0.54

Activations Density 2.205%