INDEX

Explanations

harm and violence inflicted

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

 Captured

0.73

 peligros

0.67

ogs

0.66

 Dangerous

0.65

잡

0.64

ப்படி

0.64

難しい

0.63

 catch

0.62

 fooled

0.62

ITICAL

0.62

POSITIVE LOGITS

 inflicted

2.57

 inflict

2.06

 inflicting

1.86

 infliction

1.85

 imposed

1.79

 imposition

1.57

 heaped

1.43

 directed

1.39

 endured

1.38

 suffered

1.37

Activations Density 0.221%