INDEX

Explanations

last names in citations

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

 chart

0.26

 سر

0.26

mayor

0.26

 landscape

0.25

 charting

0.25

 term

0.25

 الإ

0.24

 onslaught

0.24

POSITIVE LOGITS

 ইত্যাদি

0.26

ad

0.26

 Ilya

0.25

 Rupert

0.25

 Lionel

0.25

 Geoffrey

0.25

 Vladimir

0.24

 заявил

0.24

 கரைச

0.23

 Riccardo

0.23

Activations Density 0.003%