INDEX

Explanations

female or feminine terms

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 himself

-0.19

çĪ¶åŃĲ

-0.17

å¨¶

-0.15

èĭ±ä¿Ĭ

-0.14

å²³çĪ¶

-0.13

å¸ħæ°Ķ

-0.13

å°ıåŃĲ

-0.13

 Himself

-0.13

è¿Ļå°ıåŃĲ

-0.12

å¸ħæ°ĶçļĦ

-0.12

POSITIVE LOGITS

 herself

0.26

å¥¹ä»¬

0.18

å¥¹èĩªå·±

0.18

å¥¹ä»¬çļĦ

0.17

å¥¹åĢĳ

0.17

å«ģç»Ļ

0.17

åĩºå«ģ

0.17

åĴĮå¥¹çļĦ

0.16

æ¯įå¥³

0.16

å¨ĺå®¶

0.15

Activations Density 2.224%