INDEX

Explanations

code

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

 >=",

-0.84

клопе

-0.75

 raiſ

-0.75

 ſmall

-0.72

—

-0.71

IContainer

-0.71

]--;

-0.71

 pleaſure

-0.70

 unſ

-0.69

 Numerade

-0.68

POSITIVE LOGITS

 متعلقه

0.55

wani

0.46

ziz

0.45

toppers

0.45

 passant

0.44

 XMLHttpRequest

0.44

AndEndTag

0.43

zzi

0.43

SqlQuery

0.43

kappa

0.42

Activations Density 0.088%