INDEX

Explanations

mentions of a specific name or term that appears as "sha" in the filtered data

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

SHA

-0.59

clusal

-0.55

offrir

-0.53

IsContent

-0.51

 Lode

-0.51

ử

-0.50

jur

-0.50

TypedDataSet

-0.50

 HEADER

-0.50

 conva

-0.50

POSITIVE LOGITS

sha

2.53

sham

0.71

 समीक्षक

0.68

 Sham

0.63

RectangleBorder

0.63

 فريبيس

0.61

ᅠ

0.61

发表于

0.60

 shan

0.59

 sham

0.59

Activations Density 0.000%