INDEX

Explanations

locations and companies

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

 сосед

0.38

 Asiatic

0.37

的一种

0.37

 niż

0.36

<unused1751>

0.36

asian

0.35

 ক্লিন

0.35

 сопер

0.35

 सरा

0.35

 mathvariant

0.35

POSITIVE LOGITS

 Edition

0.43

 branch

0.42

Uma

0.39

edition

0.38

 Этот

0.38

 capítulo

0.38

ਏ

0.37

ه‌ای

0.36

 Такие

0.35

 sprechen

0.35

Activations Density 0.016%