INDEX

Explanations

legal and scientific text

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

-0.22

 prime

-0.21

-0.20

[s

-0.20

Âł

-0.20

sa

-0.20

 pain

-0.20

åĩŃ

-0.19

sur

-0.19

POSITIVE LOGITS

"';

0.30

}):

0.27

 Nunes

0.25

)))),

0.24

xon

0.24

çĽĳåĲ¬é¡µéĿ¢

0.23

rary

0.23

 $č↵

0.23

ildenafil

0.23

gnore

0.23

Activations Density 0.002%