INDEX

Explanations

will discover, learn, encounter

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

it

-1.80

if

-1.73

 after

-1.63

any

-1.52

 when

-1.47

 making

-1.42

for

-1.42

 just

-1.41

do

-1.37

so

-1.30

POSITIVE LOGITS

不仅

1.44

 firs

1.36

 zoll

1.30

 lâng

1.30

 både

1.28

 được

1.25

 první

1.25

 nejen

1.24

不但

1.23

ujesz

1.23

Activations Density 0.038%