INDEX

Explanations

references to scientific figures, illustrations, or diagrams

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

 figure

-0.82

 decimal

-0.82

 ویکی‌پدیا

-0.81

 nahilalakip

-0.75

SharedDtor

-0.70

ніципа

-0.70

 pinulongan

-0.68

awtextra

-0.68

IndentedString

-0.68

ynchronously

-0.66

POSITIVE LOGITS

 figures

1.59

figures

1.15

 FIGURES

1.02

 Figures

0.89

 cifras

0.74

fig

0.68

 numbers

0.66

 figuras

0.65

Figures

0.64

 figs

0.62

Activations Density 0.003%