INDEX

Explanations

place names, proper nouns

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

ä»ĸæĺ¯

-0.12

å¥¹æĺ¯

-0.11

ä»ĸä»¬æĺ¯

-0.10

å®ĥæĺ¯

-0.10

yna

-0.09

è¿Ļä¸ĢçĤ¹

-0.09

è¿Ļæĺ¯

-0.09

ä½łæĺ¯

-0.09

è¿Ļæĺ¯æĪĳ

-0.09

otted

-0.09

POSITIVE LOGITS

æľīåħ³éĥ¨éĹ¨

0.14

ä¸»åĬŀæĸ¹

0.11

å½ĵåľ°æĶ¿åºľ

0.11

ä¿ĿéĻ©åħ¬åı¸

0.11

ç¬¬ä¸īæĸ¹

0.11

ç®¡çĲĨéĥ¨éĹ¨

0.10

å½ĵåľ°

0.10

åĪ¶éĢłåķĨ

0.10

å¼ĢåıĳåķĨ

0.10

åĪ«äºº

0.10

Activations Density 0.147%