INDEX

Explanations

operations after equals sign

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

婼

-1.44



-1.36

-1.30

 Changer

-1.27

 dévelo

-1.26

ма

-1.24

 exécut

-1.23

 grijs

-1.23

 Prefeitura

-1.20

;%%

-1.19

POSITIVE LOGITS

呖

1.70

 учетом

1.55

佻

1.51

 отличаются

1.50

⌵

1.48

满

1.47

᷇

1.46

޸

1.45

Uwaga

1.45

vejec

1.41

Activations Density 0.003%