INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

273,612 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 system

0.82

 inhib

0.72

ystem

0.66

 actuation

0.64

 impose

0.64

 dormant

0.64

 작업

0.64

 prototype

0.63

 systems

0.63

 hinder

0.63

POSITIVE LOGITS

 news

2.36

 News

2.32

 journalist

2.22

 journalistic

2.21

 newspaper

2.16

News

2.15

 journalism

2.15

 newspapers

2.13

 noticias

2.11

 journalists

2.09

Activations Density 2.322%

No Known Activations