INDEX

Explanations

sexual content and activity

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

1.75

ة

1.65

たり

1.41

varande

1.33

К

1.31

또

1.31

য়ায়

1.30

 soport

1.30

 специалисты

1.28

としても

1.27

POSITIVE LOGITS

ﺮ

1.87

ೇತ್ರ

1.86

특별시

1.83

یل

1.77

 intercourse

1.75

 fomentar

1.73

授業

1.70

ہ

1.70

ار

1.69

 fermented

1.69

Activations Density 0.043%