INDEX

Explanations

statistical significance and false positives

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

クセル

0.78

ilerden

0.77

 구해

0.76

latan

0.75

 Collecting

0.75

root

0.71

 Collector

0.71

Diffusion

0.71

肺炎

0.71

ahaman

0.71

POSITIVE LOGITS

 False

1.01

 false

0.93

False

0.92

Bon

0.85

Bon

0.82

 correction

0.80

 corrections

0.79

 family

0.78

correction

0.77

Family

0.76

Activations Density 0.012%