INDEX

Explanations

a wide variety of words including interjections, conjunctions, articles, pronouns, and other common parts of speech, as well as some infrequent nouns and names

say "a"

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

isy

-0.48

thing

-0.46

LogFactory

-0.46

💼

-0.45

formik

-0.44

ize

-0.43

 кӀ

-0.42

hline

-0.42

lier

-0.41

̵

-0.40

POSITIVE LOGITS

1.86

as

1.34

ا

0.96

ah

0.94

aS

0.94

aas

0.93

aa

0.93

 kasarigan

0.90

aaaa

0.84

ahs

0.84

Activations Density 5.767%