INDEX

Explanations

question, command, use, see, rely

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

or

-1.90

is

-1.69

 koel

-1.43

😯

-1.39

 inga

-1.39

辈子

-1.38

 bardak

-1.36

 ofta

-1.30

 spela

-1.30

 svenska

-1.27

POSITIVE LOGITS

 навіть

1.52

ւ

1.48

who

1.45

ējās

1.41

 whose

1.37

[]):

1.36

lognese

1.30

دخ

1.30

ні

1.28

 alguien

1.27

Activations Density 0.083%