INDEX

Explanations

records, training, disclosure, annual

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

 énorme

-1.34

 différentes

-1.30

 různých

-1.25

вають

-1.23

sometimes

-1.23

怔

-1.23

 разные

-1.23

 комната

-1.22

 живет

-1.22

 Fútbol

-1.21

POSITIVE LOGITS

and

1.74

 that

1.31

 cuando

1.30

 your

1.29

 bereits

1.27

();

1.26

 tersebut

1.22

forKey

1.22

 Glaub

1.22

一月

1.18

Activations Density 0.027%