INDEX

Explanations

in

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

StructEnd

-0.97

expandindo

-0.91

tagHelperRunner

-0.89

UnusedPrivate

-0.84

 Infórmanos

-0.81

GEBURTS

-0.80

 للمعارف

-0.78

 avoient

-0.78

jooq

-0.78

 publicitaires

-0.77

POSITIVE LOGITS

0.79

an

0.50

 other

0.49

 simple

0.48

lot

0.48

 English

0.47

it

0.43

la

0.43

sa

0.42

 biology

0.42

Activations Density 0.003%