INDEX

Explanations

said

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

OGND

-0.49

 katanya

-0.44

dro

-0.41

 acus

-0.41

UnsafeEnabled

-0.40

__':

-0.40

featureID

-0.39

 للاسماء

-0.39

Попис

-0.39

labus

-0.39

POSITIVE LOGITS

 known

0.63

});

0.63

 alike

0.62

ⓧ

0.62

dieran

0.59

arest

0.59

textbackslash

0.58

ERÍA

0.58

httphttps

0.58

 written

0.58

Activations Density 0.187%