INDEX

Explanations

names followed by county

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

生きる

-1.37

 tratados

-1.29

之类的

-1.27

 mercancías

-1.25

 beträ

-1.25

 crooked

-1.23

 seguras

-1.23

 huellas

-1.20

 recoger

-1.17

 licencias

-1.14

POSITIVE LOGITS

𝐛

1.36

 sommar

1.23

 segni

1.22

of

1.21

ү

1.17

менты

1.14

шок

1.12

άν

1.12

for

1.09

":[

1.08

Activations Density 0.106%