INDEX

Explanations

describing a condition

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

 visites

-1.27

 quae

-1.19

ᵢ

-1.18

 balles

-1.14

 épaules

-1.14

 comptes

-1.13

 passagers

-1.13

apparently

-1.13

 ejus

-1.13

 derni

-1.13

POSITIVE LOGITS

 usually

1.88

can

1.75

 caused

1.67

 typically

1.59

 often

1.41

 because

1.40

 when

1.39

 Usually

1.37

may

1.33

這種

1.33

Activations Density 0.050%