INDEX

Explanations

generate text output

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

 versionName

0.46

 STEM

0.41

хих

0.39

収録曲

0.39

 ከመ

0.38

 negotiators

0.38

 immédiatement

0.38

 जिक्र

0.38

বিজ্ঞান

0.38

 inférieure

0.37

POSITIVE LOGITS

 coherent

0.63

 челове

0.50

 human

0.50

 intelligent

0.49

 helpful

0.48

 text

0.47

 informative

0.46

 remarkably

0.45

 natural

0.44

 communicative

0.44

Activations Density 0.085%