INDEX

Explanations

citations and parentheticals

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

Ð¸Ð½Ð´Ð¸Ð²Ð¸Ð´

-0.25

 Ð¿ÑĢÐ¸ÑıÑĤÐ½

-0.25

Ð¸Ð½Ð´Ð¸Ð²

-0.24

íĹĢ

-0.21

ä¹Łä¸įéĶĻ

-0.21

ÐµÑģÑĤÐµÑģÑĤÐ²ÐµÐ½Ð½

-0.21

ÑĢÐµÐ³Ð¸

-0.21

Ð¿ÑĢÐ°ÐºÑĤÐ¸Ðº

-0.21

åı¯èĥ½åŃĺåľ¨

-0.21

è¿Ķ

-0.21

POSITIVE LOGITS

 famously

0.38

 famous

0.25

 notoriously

0.21

itan

0.21

 infamous

0.21

èĳĹåĲįçļĦ

0.21

èĳĹåĲį

0.20

ì£ł

0.20

classic

0.20

 bask

0.20

Activations Density 1.191%