INDEX

Explanations

names and 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»İåİ»å¹´

-0.13

ä»Ĭå¹´ä»¥æĿ¥

-0.13

æĺ¨

-0.13

æĺİå¹´

-0.12

åľ¨ä»Ĭå¹´

-0.12

ä»Ĭå¹´

-0.12

çĽ®åīįæŃ£åľ¨

-0.11

è¿ĳæĹ¥

-0.11

æĺ¨æĻļ

-0.11

æľ¬æľĪ

-0.11

POSITIVE LOGITS

å½ĵæĹ¶

0.18

å½ĵæĹ¶çļĦ

0.16

æĹ¶ä»»

0.15

çķ¶æĻĤ

0.15

éĤĵå°ıå¹³

0.13

æĸ°ä¸ĸçºª

0.13

æĪĳå½ĵæĹ¶

0.13

éĤ£æĹ¶

0.12

éĤ£æĹ¶åĢĻ

0.12

 ëĭ¹ìĭľ

0.12

Activations Density 0.894%