INDEX

Explanations

mathematical notation and URLs

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

 will

-1.41

“

-1.39

或

-1.34

もう

-1.33

 others

-1.30

速度

-1.30

ersburg

-1.27

器具

-1.27

ментом

-1.27

is

-1.25

POSITIVE LOGITS

了解更多

1.52

つづく

1.50

 solicitó

1.48

苾

1.47

 OGSÅ

1.45

糗

1.42

是一位

1.39

kimono

1.38

INSEE

1.38

 aprobó

1.38

Activations Density 0.015%