INDEX

Explanations

the word "almost"

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

IBD

-0.84

Folks

-0.82

complexContent

-0.78

 Polity

-0.76

browserify

-0.75

onViewCreated

-0.75

 Purdy

-0.74

 Gentry

-0.74

 Roughly

-0.74

énario

-0.73

POSITIVE LOGITS

idist

0.65

 Alha

0.61

סף

0.60

 }}$}

0.60

solete

0.59

önt

0.59

ssssssss

0.58

ängt

0.57

apour

0.57

Kann

0.57

Activations Density 0.011%