INDEX

Explanations

various non-English characters

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

 anomal

-0.23

èĩªæĿ¥

-0.22

ä»»ä½ķäººéĥ½

-0.22

Ð¿ÑĢÐ¾ÑĦÐµÑģÑģÐ¸Ð¾Ð½Ð°Ð»

-0.22

Ð¸Ð½Ð´Ð¸Ð²Ð¸Ð´

-0.22

æĺ¯ä»Ģä¹Īåĳ¢

-0.21

 Ellis

-0.21

ç³ķ

-0.21

çĽ¸å¯¹è¾ĥ

-0.21

èĮĥåĽ´åĨħ

-0.21

POSITIVE LOGITS

çŃīçŃī

0.54

etc

0.48

 blah

0.45

 various

0.43

ä¹ĭç±»çļĦ

0.42

çŃīåĨħå®¹

0.41

ä¹ĭç±»

0.41

etc

0.39

çļĦåĲĦç§į

0.36

åĲĦç§į

0.35

Activations Density 0.129%