INDEX

Explanations

first, second, third, first time

match specific properties

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

lian

0.50

 policy

0.49

 literary

0.49

 loudly

0.48

lobe

0.48

lam

0.47

lamb

0.46

lains

0.46

kom

0.45

 verb

0.45

POSITIVE LOGITS

 ریز

0.50

дова

0.50

 হওয়া

0.48

Vanilla

0.47

زی

0.47

したら

0.47

Catagory

0.45

𝕤

0.45

ธุรก

0.45

羰

0.45

Activations Density 0.000%