INDEX

Explanations

loss, Rusty metal

risky consequences and legal issues

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

ä

0.48

äische

0.46

 අතර

0.44

 зберіга

0.43

anı

0.41

шение

0.41

aż

0.41

银

0.41

ани

0.41

 zakresie

0.40

POSITIVE LOGITS

debug

0.46

 flashy

0.43

 jungles

0.43

 первые

0.42

 trường

0.42

福島

0.42

 yung

0.41

 trial

0.41

 debug

0.41

너무

0.41

Activations Density 0.000%