INDEX

Explanations

pronouns referring to people

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

 also

-1.70

 their

-1.62

 pulgadas

-1.45

Also

-1.30

 from

-1.20

 myös

-1.17

 نیز

-1.16

They

-1.16

 following

-1.16

 etiam

-1.13

POSITIVE LOGITS

 этих

1.45

if

1.35

这些

1.25

künfte

1.23

Adverti

1.20

 แล้ว

1.19

桫

1.16

 هذه

1.14

 ilyen

1.13

 ponú

1.13

Activations Density 0.033%