INDEX

Explanations

references to citations

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

########.

-0.95

 Jayne

-0.79

 برانيه

-0.77

usammen

-0.73

nito

-0.70

 Mandy

-0.69

 Stars

-0.68

 ModelAndView

-0.68

 Melody

-0.68

Stars

-0.66

POSITIVE LOGITS

CR

1.62

CR

1.53

cr

1.08

Crus

0.97

 CRISPR

0.96

HCR

0.94

cr

0.88

Cra

0.86

crv

0.86

CRU

0.86

Activations Density 0.248%