INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

é¢Ģ

-0.21

 stars

-0.21

çĸ®

-0.20

 only

-0.19

Lag

-0.19

 other

-0.18

å

-0.18

à¸łà¸²à¸ŀ

-0.18

 none

-0.18

_ROWS

-0.18

POSITIVE LOGITS

');↵↵↵↵

0.24

fkk

0.24

akest

0.24

 lowes

0.23

 Hentai

0.23

rious

0.23

rescia

0.22

åĨ°æ·ĩ

0.22

".↵↵↵↵

0.22

\"",↵

0.22

Activations Density 0.001%

No Known Activations