INDEX

Explanations

general statements and qualifications

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

 exager

0.50

 exaggerated

0.43

 exag

0.43

 exagger

0.43

 ofta

0.42

any

0.39

 exaggeration

0.39

 decept

0.39

 sometimes

0.39

 گاه

0.39

POSITIVE LOGITS

 Generally

1.04

Generally

1.02

 generally

0.96

generally

0.95

 generalmente

0.75

一般来说

0.75

 일반적으로

0.72

 umumnya

0.71

一般

0.64

 généralement

0.59

Activations Density 0.271%