INDEX

Explanations

present study

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

 Urinary

-0.77

Herbert

-0.77

 Herbert

-0.75

iach

-0.75

yen

-0.73

 Barça

-0.69

FileUtils

-0.66

StatusCodes

-0.66

ческое

-0.65

atern

-0.64

POSITIVE LOGITS

hul

0.75

でもない

0.69

 Национальный

0.68

Dev

0.65

 migrant

0.65

Hansen

0.65

жмите

0.64

 Clin

0.64

 personales

0.63

mande

0.62

Activations Density 0.044%