INDEX

Explanations

places in the text where lists of numbers appear

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

 للمعارف

-0.85

InitVars

-0.82

SourceChecksum

-0.77

featureID

-0.71

 ſche

-0.69

DeleteBehavior

-0.68

berdayakan

-0.66

 ſtate

-0.65

PhysRev

-0.64

 houſe

-0.64

POSITIVE LOGITS

makeText

0.60

prefixer

0.54

MemoryWarning

0.47

 Merk

0.46

ExecuteReader

0.44

Gdx

0.44

Persön

0.43

جوايز

0.43

RenderAtEndOf

0.43

prüche

0.42

Activations Density 0.206%