INDEX

Explanations

known for

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

æĪĳè¯´

-0.29

PropertyParams

-0.24

çĲĨçĶ±

-0.23

éĹ®éĹ®

-0.23

éĻĲå®ļ

-0.23

è¯»èĢħ

-0.23

ä¸ĭæ¬¡

-0.22

åĲĪæł¼

-0.22

çľĭçľĭ

-0.22

àª³

-0.21

POSITIVE LOGITS

åħ¶

0.27

 ÑģÐ²Ð¾ÐµÐ¹

0.27

its

0.27

 being

0.25

ently

0.24

å®ĥçļĦ

0.24

forming

0.23

being

0.23

å®ĥæĺ¯

0.22

çļĦçľ¼åħī

0.21

Activations Density 0.038%