INDEX

Explanations

IDENTIFY victims of harm

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

`${

0.84

 AMOLED

0.71

 covalent

0.69

รือ

0.66

perclip

0.66

 coval

0.65

 polygonal

0.65

 monolithic

0.65

 solides

0.64

 alphanumeric

0.64

POSITIVE LOGITS

Identify

0.79

 Victims

0.75

 Identify

0.75

被害

0.74

identify

0.73

 конфлик

0.72

 persec

0.72

 禁止

0.72

仇

0.72

 víctimas

0.72

Activations Density 0.179%

No Known Activations