INDEX

Explanations

came back short

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Boxing

-0.76

odyear

-0.73

jeh

-0.72

 Grill

-0.71

rdida

-0.71

oblast

-0.70

 Jesuit

-0.70

 Brownian

-0.69

Примечания

-0.69

 descente

-0.68

POSITIVE LOGITS

 came

1.79

 coming

1.78

 come

1.67

Came

1.64

 comes

1.59

Coming

1.59

coming

1.52

 Came

1.45

Come

1.44

came

1.44

Activations Density 0.063%