INDEX

Explanations

list items starting with numbers or punctuation

your likes or preferences

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

 descend

0.45

 في

0.44

 لكن

0.43

注目

0.42

いますが

0.41

 escapar

0.41

 пои

0.41

 compartir

0.41

यो

0.41

cken

0.40

POSITIVE LOGITS

 Reigns

0.55

 Brody

0.54

 Gerät

0.50

 Denny

0.50

 Asked

0.50

 víct

0.48

Zaw

0.47

 Coins

0.47

Mei

0.47

 Samples

0.46

Activations Density 0.001%