INDEX

Explanations

visual separators in documents, especially long underlines

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

 estimés

-0.81

 Hitchcock

-0.71

 Kans

-0.71

 Beres

-0.69

Geografi

-0.68

 caes

-0.65

 Balk

-0.63

LookAnd

-0.63

 Popper

-0.63

 Barna

-0.63

POSITIVE LOGITS

________________

1.06

___

0.75

►

0.63

 információk

0.60

0.59

TestingModule

0.55

édrale

0.54

 desierto

0.54

 إذ

0.53

Activations Density 0.004%