INDEX

Explanations

my / mine

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

æĪĳä»¬çŁ¥éģĵ

-0.24

 presumably

-0.23

 dirent

-0.21

 plagiar

-0.21

xlim

-0.20

æ§ĺãĢħ

-0.20

 yourselves

-0.20

 ðŁĺī↵↵

-0.20

 optarg

-0.20

 POLITICO

-0.19

POSITIVE LOGITS

my

0.39

 myself

0.35

ä½¿æĪĳ

0.29

æĪĳå¯¹

0.29

å½ĵæĪĳ

0.29

äºĨæĪĳçļĦ

0.28

åĽłä¸ºæĪĳ

0.27

æĪĳå°±

0.27

 minha

0.27

æĪĳåľ¨

0.26

Activations Density 5.270%