INDEX

Explanations

words related to politics, values and group affiliation

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

No Comments

Negative Logits

figcaption

-0.70

 naturellement

-0.64

 opérateur

-0.60

στό

-0.60

asantry

-0.60

venser

-0.59

 fallu

-0.58

 حاضر

-0.57

 prêt

-0.57

lages

-0.57

POSITIVE LOGITS

AndEndTag

0.72

Geplaatst

0.64

 كومونز

0.59

RenderAtEndOf

0.55

InstrumentedTest

0.54

PhysRevLett

0.53

<bos>

0.49

iastical

0.49

IBar

0.48

GEBURTSDATUM

0.47

Activations Density 2.146%