INDEX

Explanations

code comments

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 thingy

-1.22

ᐳ

-1.21

 ulica

-1.21

 extraordinaire

-1.20

挙げ

-1.16

齟

-1.10

 sensation

-1.09

 retten

-1.08

 ویکی‌پدیا

-1.06

りましたが

-1.06

POSITIVE LOGITS

 noqa

1.58

<--

1.48

etches

1.38

 omfatt

1.30

 necesario

1.28

 понадобится

1.28

お楽しみに

1.27

<-

1.27

的花

1.26

!<

1.24

Activations Density 0.036%