INDEX

Explanations

harming yourself or others

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 causes

1.56

 ages

1.38

 children

1.37

 poorest

1.36

 descend

1.30

 collide

1.29

 darkest

1.29

 villagers

1.28

 migrants

1.27

 males

1.27

POSITIVE LOGITS

őség

1.67

؛

1.66

。"

1.60

 الاختبار

1.57

 meski

1.56

ProductRunnable

1.56

 هند

1.51

 Hinweis

1.50

'،

1.48

 wereld

1.47

Activations Density 0.021%

No Known Activations