INDEX

Explanations

Things

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

LookAnd

-0.83

 صوتيه

-0.76

findpost

-0.74

 Rasul

-0.71

 ddelweddau

-0.71

RegressionTest

-0.70

 CHtml

-0.68

 ostavi

-0.67

utnik

-0.64

rrh

-0.63

POSITIVE LOGITS

 demand

0.46

Ar

0.44

 demands

0.43

 over

0.41

by

0.40

wear

0.40

 call

0.40

 time

0.40

 miss

0.40

via

0.39

Activations Density 0.017%