INDEX

Explanations

Casting

articles with names of people

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

 ſtate

-0.71

NewRow

-0.68

koper

-0.68

]--;

-0.65

Efq

-0.64

asyarakat

-0.63

 ſta

-0.62

 houſe

-0.62

IVEREF

-0.60

Eſ

-0.60

POSITIVE LOGITS

 defStyle

0.56

 Casting

0.49

#+#

0.48

Casting

0.48

 casting

0.48

UrlResolution

0.47

KeySpec

0.45

Fns

0.44

ModelForm

0.43

casting

0.42

Activations Density 1.779%