INDEX

Explanations

crime and violence

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

æľ¬çĿĢ

-0.24

 Portions

-0.24

plat

-0.24

.Arg

-0.23

immers

-0.23

 yourselves

-0.22

äº«åıĹåĪ°

-0.22

èį£å¹¸

-0.22

ãģĴ

-0.22

edly

-0.21

POSITIVE LOGITS

 victim

0.26

 crime

0.26

å«Įçĸĳäºº

0.26

 encrypted

0.26

ä¾¦

0.26

çĬ¯ç½ª

0.26

è¢«å®³

0.25

è¢«çĽĹ

0.25

Crime

0.24

Unsafe

0.23

Activations Density 0.006%