INDEX

Explanations

Johns Hopkins University

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

-2.61

-2.48

 ciencia

-2.36

 constitución

-2.34

เพื่อ

-2.30

想

-2.23

然

-2.23

–

-2.22

 欣赏

-2.22

 asamblea

-2.17

POSITIVE LOGITS

雰囲

2.69

個人的には

2.61

After

2.53

要把

2.52

媖

2.47

.’

2.33

うーん

2.33

㈲

2.31

 dédié

2.28

ちな

2.27

Activations Density 0.019%