INDEX

Explanations

questions or clarifications

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

Halloween

0.41

 Halloween

0.40

 ベッド

0.39

になって

0.38

 danno

0.37

 হয়ে

0.37

 dzięki

0.37

 кіль

0.37

 Від

0.35

 halloween

0.35

POSITIVE LOGITS

 femininity

0.38

knn

0.37

 Öffentlichkeit

0.37

analyzer

0.36

atif

0.36

pub

0.34

 bullshit

0.34

abajo

0.34

parcel

0.34

카

0.34

Activations Density 0.000%