INDEX

Explanations

have been

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

_equiv

-0.23

å°±å¾Ĺ

-0.23

geist

-0.22

à¸²à¸¢à¸Ļ

-0.21

é¡¶ç«¯

-0.20

ëĭ·

-0.20

ç§Ĩ

-0.20

åıįæĺłåĩº

-0.20

çĶ±ä¸ŃåĽ½

-0.20

å¯¹äºİæĪĳä»¬

-0.20

POSITIVE LOGITS

 plenty

0.28

å¥½åĩłä¸ª

0.25

ä¸įå°ĳ

0.24

å¾Ĺå¤ļ

0.23

 nowhere

0.22

ä¸°å¯ĮçļĦ

0.22

åĩłä½į

0.22

å¥½å¤ļ

0.22

bon

0.22

çĮľæµĭ

0.22

Activations Density 0.156%