INDEX

Explanations

like / likes / liked

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

ÑĢÐµÐ³Ð¸

-0.20

Ð¸Ð½Ð´Ð¸Ð²Ð¸Ð´

-0.19

loom

-0.18

Ð¸Ð½Ð´Ð¸Ð²

-0.18

ĲèĹı

-0.18

hone

-0.18

Ð±Ð»Ð°Ð³Ð¾

-0.17

 Ð¿Ð¾ÑģÐºÐ¾Ð»ÑĮ

-0.17

ãĤ¤ãĥ³ãĤ¿ãĥ¼ãĥį

-0.16

ÑĩÑĢÐµÐ¶Ð´ÐµÐ½

-0.16

POSITIVE LOGITS

äºĨå¾Īä¹ħ

0.21

ably

0.20

æł·çļĦ

0.18

å¾Īåĸľæ¬¢

0.18

å¾Ĺå¾Ī

0.18

ewise

0.18

ãģįãģ¦

0.18

able

0.18

ãģĦãģı

0.17

 ÑĤÐ¾Ð³Ð¾

0.17

Activations Density 0.040%