INDEX

Explanations

consent and voluntary

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

 टिप्प

0.41

 gần

0.38

 रौ

0.38

屏蔽

0.38

点评

0.36

 неста

0.36

קו

0.35

에

0.35

 апре

0.35

স্থান

0.34

POSITIVE LOGITS

 voluntary

2.13

 voluntarily

2.08

 Voluntary

1.83

voluntary

1.71

 willingly

1.70

 volont

1.70

 volunt

1.67

 স্বেচ্ছ

1.47

 consent

1.31

 consensual

1.27

Activations Density 0.090%