INDEX

Explanations

gender policy changes

contrasting or sequential items

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

ήθ

0.48

бята

0.45

নাট

0.44

Algebra

0.44

pheus

0.44

ModelAttribute

0.43

algèbre

0.43

ксе

0.43

эль

0.42

ᅬ

0.42

POSITIVE LOGITS

 Bukan

0.56

 Thank

0.55

NN

0.51

 touristic

0.51

 يت

0.50

 divisive

0.49

 nejsou

0.49

 موب

0.48

 ከአ

0.48

 TripAdvisor

0.47

Activations Density 0.008%