INDEX

Explanations

vocabulary and non-english words

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

 contre

0.47

 compliance

0.46

 refrained

0.46

der

0.45

 eher

0.44

기

0.44

 posiblemente

0.44

 tidak

0.43

 רי

0.43

POSITIVE LOGITS

 Vocabulary

0.44

Vocabulary

0.44

 Extras

0.43

 शब्दों

0.42

Preferences

0.42

सपने

0.41

传入

0.40

 शब्दा

0.40

Extras

0.39

belle

0.39

Activations Density 0.008%