INDEX

Explanations

or greater, too heavily

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

QA

0.28

unque

0.27

 Took

0.27

Mod

0.26

のみ

0.26

年以上

0.26

 więcej

0.26

penas

0.25

Yo

0.25

Fireworks

0.25

POSITIVE LOGITS

 targets

0.27

 amorphous

0.27

CHEMY

0.27

 codecs

0.26

 desaf

0.26

 harmonization

0.25

 discussions

0.25

 spheres

0.25

 phrases

0.25

 palindrome

0.25

Activations Density 0.000%