INDEX

Explanations

place names followed by comma

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

 ÐĲÐ»ÐµÐºÑģÐ°Ð½

-0.27

à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ

-0.26

 à¹Ģà¸¡à¸©

-0.26

 à¸¡à¸ģà¸£

-0.24

à¸Ħà¸ĵà¸°à¸ģà¸£à¸£à¸¡

-0.24

 à¸ŀà¸¤à¸©

-0.23

 Ð¼Ð¾ÑīÐ½

-0.23

 ÐŁÐ¾ÑĩÐµÐ¼

-0.22

 ÐĶÐ¼Ð¸ÑĤÑĢ

-0.21

 Ð¼ÐµÑĢÐ¾Ð¿

-0.21

POSITIVE LOGITS

fkk

0.25

 spep

0.22

.Xr

0.21

 milfs

0.20

.setter

0.20

rÃªt

0.19

<",

0.19

 iNdEx

0.19

{?}

0.19

ðŁĺĴ

0.19

Activations Density 0.021%