INDEX

Explanations

health care, consortium, respond

political figures

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

اں

0.53

менов

0.51

有时候

0.49

 బ్యా

0.49

 හෝ

0.47

暝

0.47

遑

0.47

城堡

0.47

 تشدد

0.47

MARKS

0.46

POSITIVE LOGITS

ed

0.51

 been

0.51

for

0.50

 Kend

0.48

0.46

Rh

0.46

dix

0.46

 imitated

0.45

 Amusement

0.45

 cropland

0.45

Activations Density 0.000%