INDEX

Explanations

recent study or studies

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

hay

-0.09

 ÑģÐ¾Ð±ÑģÑĤÐ²ÐµÐ½Ð½Ð¾

-0.09

Ð´ÐµÐ¹

-0.09

æĺ¯ä¸Ģä»¶

-0.08

han

-0.08

-too

-0.08

çĤ¹å¤ļ

-0.08

DDL

-0.08

ENSE

-0.08

è´£ä»»ç¼ĸè¾ĳ

-0.08

POSITIVE LOGITS

çłĶç©¶è¡¨æĺİ

0.26

è°ĥæŁ¥æĺ¾ç¤º

0.19

 studies

0.17

 study

0.15

çłĶç©¶

0.14

 recent

0.14

æľĢè¿ĳ

0.13

æĬ¥åĳĬæĺ¾ç¤º

0.12

recent

0.12

 Studies

0.12

Activations Density 0.273%