INDEX

Explanations

doing something again

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

 verschillende

-1.70

紲

-1.57

 obiet

-1.57

 gustó

-1.55

 Fakta

-1.53

牁

-1.52

the

-1.52

blätter

-1.49

 }}$,

-1.47

 Tentang

-1.46

POSITIVE LOGITS

-\

1.59

),

1.54

–

1.45

 symbol

1.42

,,

1.39

1.38

).

1.34

quiao

1.34

 sorta

1.33

Activations Density 0.010%