INDEX

Explanations

David followed by last name

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

ingly

-0.20

Ð°ÑİÑĤÑģÑı

-0.17

ved

-0.17

velt

-0.16

eed

-0.16

çľĩ

-0.16

Ø±

-0.16

è¿Ļä¹Łæĺ¯

-0.16

esa

-0.15

hots

-0.15

POSITIVE LOGITS

sons

0.23

sson

0.21

son

0.20

raison

0.17

ãĤĪãģĨãģª

0.17

ÑģÐ¾Ð½

0.17

acre

0.16

åĦĭ

0.16

 bÃ¨

0.15

ä½Ĺ

0.15

Activations Density 0.027%