INDEX

Explanations

ance

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

ance

-1.03

ly

-0.70

ANCE

-0.67

 hostile

-0.66

ment

-0.65

self

-0.63

 aggressive

-0.63

ness

-0.62

dle

-0.62

nya

-0.60

POSITIVE LOGITS



1.00

 '\\;'

0.87

makeText

0.86

ChildScrollView

0.85

Amicalement

0.83

PreferredItem

0.82

 SafeMath

0.82

addCriterion

0.80

featureID

0.79

 Мексичка

0.79

Activations Density 0.843%