INDEX

Explanations

technical/scientific texts

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

Jereo

-0.85

dafx

-0.73

featureID

-0.66

 חיצוניים

-0.66

헌

-0.65

 ویکی‌پدیا

-0.63

⎨

-0.63

 Bourgoin

-0.60

 Haines

-0.59

 Urqu

-0.59

POSITIVE LOGITS

ेशा

0.47

CloseOperation

0.47

مثلة

0.45

 Cover

0.44

/></

0.44

 cover

0.43

 />';

0.43

getOut

0.42

copg

0.42

awt

0.40

Activations Density 0.001%