INDEX

Explanations

structured text and symbols

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ଗ

0.40

 entsprechenden

0.38

ᓲ

0.38

 subsections

0.38

 antiguos

0.37

DependentUpon

0.37

 contrats

0.37

调研

0.36

 activities

0.36

ণ্য

0.36

POSITIVE LOGITS

 Ministry

0.48

 Cartoon

0.42

 Marriage

0.41

 Tower

0.41

 बैड

0.41

0.40

 Minister

0.40

 Ugly

0.40

 Bird

0.39

ഃ

0.39

Activations Density 0.001%