INDEX

Explanations

words and phrases that appear to introduce examples

such

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

########.

-0.78

TagMode

-0.64

 exemplaires

-0.58

 générations

-0.57

 bouteilles

-0.57

 löyty

-0.56

 périodes

-0.55

ագրություններ

-0.55

EDEFAULT

-0.55

 unités

-0.53

POSITIVE LOGITS

 Helms

0.57

kmäler

0.57

:✨

0.57

has

0.52

such

0.52

 ello

0.52

alva

0.51

sass

0.50

 such

0.50

an

0.49

Activations Density 5.725%