INDEX

Explanations

disregard, neglect, disrespect

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

ከናወ

0.85

 生成

0.79

找到

0.77

実感

0.75

 അവസ്ഥ

0.74

序

0.73

 สื

0.72

 retrouver

0.72

 കണ്ടെത്ത

0.72

reachable

0.72

POSITIVE LOGITS

 disregard

2.40

 neglect

2.29

 disrespect

2.28

 ignoring

2.21

 neglecting

2.13

 disrespectful

2.06

 ignore

2.06

 ignores

2.05

 disregarding

2.04

 neglects

2.01

Activations Density 0.291%