INDEX

Explanations

fire

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 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

 Fire

-0.62

 fire

-0.59

Fire

-0.55

fire

-0.51

 FIRE

-0.50

al

-0.48

 fires

-0.48

 Green

-0.47

at

-0.45

 doch

-0.44

POSITIVE LOGITS

MigrationBuilder

0.72

WithIOException

0.69

utilisons

0.68

enido

0.65

 يتيمه

0.64

曖昧さ回避

0.62

 autorytatywna

0.62

Kesimpulan

0.61

discus

0.60

Activations Density 0.080%