INDEX

Explanations

concepts followed by punctuation

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

גד

0.42

Story

0.40

Trans

0.39

技

0.38

Additional

0.38

 التف

0.37

ጉ

0.36

 안내

0.36

 Trans

0.35

Safety

0.35

POSITIVE LOGITS

 doesn

0.43

ioen

0.41

 எடுத்துக்

0.39

uyan

0.39

 завжди

0.39

μου

0.39

 altid

0.39

 excellently

0.39

 esigen

0.38

 Doesn

0.38

Activations Density 0.000%