INDEX

Explanations

destruction and damage

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

 смерти

0.50

 الحكم

0.41

 героя

0.41

 Фургала

0.40

 decentral

0.39

🙋

0.39

代谢

0.39

句話

0.39

 қай

0.39

 superviv

0.38

POSITIVE LOGITS

Destroy

0.70

 destruction

0.70

destroyed

0.68

 destroyed

0.66

 Destroy

0.66

 বিনষ্ট

0.64

破壊

0.63

 destroys

0.63

 Destruction

0.61

 destroying

0.61

Activations Density 0.056%