INDEX

Explanations

common, popular, typical

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

 réellement

0.98

 véritable

0.95

 esclusivamente

0.93

 Truly

0.91

 Literally

0.88

 진짜

0.87

 genuinely

0.84

本当に

0.84

 literalmente

0.83

 defies

0.81

POSITIVE LOGITS

 popular

1.99

popular

1.77

常用的

1.76

Popular

1.74

 common

1.73

常見

1.72

 commonly

1.71

常见的

1.66

 популяр

1.61

常用

1.58

Activations Density 1.065%