INDEX

Explanations

stopping speech

interrupting speech

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

].”

0.49

 sedangkan

0.41

 بينما

0.40

]?.

0.39

睢

0.38

 মেলে

0.38

].)

0.38

 வய

0.38

 tổn

0.37

ரிகிறது

0.37

POSITIVE LOGITS

 prevent

0.75

 Prevent

0.70

 جلوگیری

0.69

 prevented

0.67

Prevent

0.66

 Preventing

0.66

prevent

0.65

 preventing

0.64

 prevents

0.61

防止

0.55

Activations Density 0.008%