INDEX

Explanations

dosage and instructions

predicting next word

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

ע

0.65

 GARD

0.52

麗

0.52

Doctors

0.50

 Gardening

0.48

MGMT

0.47

Clin

0.46

дки

0.46

Vý

0.46

Noir

0.46

POSITIVE LOGITS

\{\

0.47

 latitudes

0.47

²

0.45

suf

0.44

vore

0.43

 kinds

0.43

hover

0.43

 ages

0.43

 فبراير

0.43

turned

0.42

Activations Density 0.002%