INDEX

Explanations

people and their actions

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

אָ

0.37

 hyphen

0.35

 correctement

0.34

סף

0.33

 hereinafter

0.33

 proverbial

0.33

рых

0.33

従来

0.32

 pesky

0.32

br

0.32

POSITIVE LOGITS

They

0.37

வரும்

0.34

することが

0.33

urgo

0.33

苏州

0.33

Glasgow

0.33

 especially

0.32

Especially

0.32

Relatives

0.32

 அனுப

0.32

Activations Density 0.000%