INDEX

Explanations

all, us, people, everyone

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

וּ

-1.30

atized

-1.27

Ξ

-1.27

lizes

-1.23

taya

-1.20



-1.16

げた

-1.16

 cafetería

-1.12

 ouvriers

-1.10

/…

-1.09

POSITIVE LOGITS

According

1.30

 behaupten

1.18

1.13

 arvio

1.13

越来越

1.12

 health

1.09

larınız

1.09

 怎样

1.08

 chrétienne

1.08

・・・・・

1.08

Activations Density 0.231%