INDEX

Explanations

for something

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

ãģĬ

-0.12

ãģĻãģĲãģ«

-0.12

æľīä¸Ģç§į

-0.11

ropol

-0.11

ãģĤãĤĭ

-0.10

ãģĬè©±

-0.10

åĩ¡äºĭ

-0.10

ãĤĤãģĨ

-0.10

ãģĻãģ§ãģ«

-0.10

ãģĬå¾Ĺ

-0.10

POSITIVE LOGITS

bidden

0.14

/by

0.13

/from

0.12

 sake

0.11

 both

0.11

ä»Ģä¹Īåĳ¢

0.11

/about

0.10

wards

0.10

 eventual

0.10

chten

0.10

Activations Density 0.721%