INDEX

Explanations

time and action

refusing explicit or harmful requests

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

.).

0.51

BTW

0.46

)."

0.45

%).

0.45

btw

0.45

'."

0.44

?).

0.43

했고

0.43

.'"

0.42

’.”

0.41

POSITIVE LOGITS

<0xC2>

0.96

 […]

0.64

 있는데요

0.54

 🙂

0.50

 😀

0.49

ㅎㅎ

0.49

 例文帳に追加

0.48

 …………

0.47

 Öncelikle

0.47

 XNUMX

0.46

Activations Density 0.187%