INDEX

Explanations

crimes and dissidents

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

 ভারতবর্ষে

0.84

 wereld

0.80

ニューヨーク

0.79

 Америки

0.76

 세계

0.75

 ভারতবর্ষ

0.75

 Madison

0.74

 Zuck

0.74

 HIPAA

0.74

 世界

0.74

POSITIVE LOGITS

 insults

1.01

 allegedly

0.98

 denunci

0.98

 insulting

0.97

 reportedly

0.96

 prefect

0.94

 blasp

0.94

 provincial

0.93

 hool

0.93

 policemen

0.93

Activations Density 0.055%