INDEX

Explanations

words that soften a negative statement

scientific/technical context

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

 '\\;'

-0.56

MLLoader

-0.52

UnsafeEnabled

-0.49

DOCTYPE

-0.47

SOUNDBITE

-0.46

achau

-0.45

iyor

-0.45

inthe

-0.44

sterne

-0.44

garn

-0.42

POSITIVE LOGITS

 AttributeSet

0.89

 arbitrary

0.79

ViewImports

0.79

 arbitrarily

0.78

 unnatural

0.78

存于互联网档案馆

0.73

 contrived

0.72

脚注の使い方

0.71

arbitrary

0.71

iculous

0.70

Activations Density 3.235%