INDEX

Explanations

code, technical documentation

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

ValueStyle

-0.75

leggio

-0.57

MockBean

-0.56

 Legendre

-0.55

 Allociné

-0.54

gestone

-0.54

fromCharCode

-0.54

cycling

-0.54

'{@

-0.53

')['

-0.53

POSITIVE LOGITS

#!/

0.49

#+#

0.48

 Clara

0.44

rungsseite

0.40

шибка

0.39

förs

0.38

 SafeMath

0.37

Nia

0.37

äld

0.37

Clara

0.36

Activations Density 0.010%