INDEX

Explanations

politics or government

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.56

 AssemblyCulture

-0.49

<-

-0.49

us

-0.47

makeConstraints

-0.47

 createContext

-0.47

 rabies

-0.46

 poda

-0.45

“

-0.45

-0.44

POSITIVE LOGITS

<bos>

0.80

ografija

0.64

resaid

0.61

esez

0.60

éndolo

0.60

Życiorys

0.59

preduce

0.58

ernalia

0.57

phazard

0.56

criminator

0.55

Activations Density 0.593%