INDEX

Explanations

nearly, almost, quite, more, only, both

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

 ÐŁÐ¾ÑĩÐµÐ¼

-0.28

ä»Ģä¹Īåĳ¢

-0.24

æĪĳ

-0.23

former

-0.22

åĪĴåĪĨ

-0.22

traÃ®n

-0.22

éĿŀ

-0.21

å®ĥ

-0.21

 ÐĲÐ»ÐµÐºÑģÐ°Ð½

-0.21

èĩªçĦ¶æĺ¯

-0.20

POSITIVE LOGITS

icamente

0.27

å¹´ä¹ĭä¹ħ

0.26

lessly

0.23

efore

0.23

ingga

0.22

astery

0.22

ynchronously

0.21

via

0.21

çĪ±ç¾İ

0.21

ä¹ħäºĨ

0.21

Activations Density 0.241%