INDEX

Explanations

fic rating categorization

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

 Pages

0.40

页

0.39

फेर

0.39

雪

0.39

 Knox

0.39

 pages

0.38

advance

0.38

KC

0.38

 advance

0.38

 snow

0.38

POSITIVE LOGITS

Tag

0.44

Dataset

0.43

 Groundwater

0.43

 Priya

0.42

➢

0.42

Wat

0.41

Tag

0.40

Watson

0.40

tag

0.39

 लाइब्रेरी

0.39

Activations Density 0.003%