INDEX

Explanations

announcing new initiatives

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

 разных

-1.73

 різних

-1.65

 both

-1.60

 different

-1.52

 jeweiligen

-1.45

 various

-1.44

、

-1.42

 each

-1.41

 these

-1.39

 freundlich

-1.33

POSITIVE LOGITS

in

1.72

to

1.55

ктором

1.27

his

1.27

 katk

1.26

 様子

1.24

違和

1.23

そも

1.23

 لأنه

1.21

 وذلك

1.18

Activations Density 0.105%