INDEX

Explanations

loss

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

SequentialGroup

-0.79

 propOrder

-0.78

makeConstraints

-0.68

 >=",

-0.68

 invokingState

-0.66

 snippetHide

-0.63

IsContent

-0.61

 autorytatywna

-0.58

colgroup

-0.56

 للمعارف

-0.56

POSITIVE LOGITS

시오

0.51

 StringField

0.50

Cinderella

0.48

udit

0.48

 Sill

0.47

 Cheyenne

0.46

gencies

0.46

isses

0.46

ceptre

0.46

eclipse

0.45

Activations Density 0.002%