INDEX

Explanations

list items and relationships

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 homosexual

-0.09

 pornography

-0.09

 Sexual

-0.09

 sexual

-0.08

Porn

-0.08

attr

-0.08

 porn

-0.08

 sanction

-0.07

 masturb

-0.07

 Erotic

-0.07

POSITIVE LOGITS

 adventurous

0.16

TBD

0.15

 adventures

0.14

XYZ

0.14

 blah

0.13

Adventure

0.13

xyz

0.13

 adventure

0.12

XXX

0.12

XX

0.11

Activations Density 0.030%

No Known Activations