INDEX

Explanations

separators followed by standard labels

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

𒋾

0.45

 subtlet

0.42

LayerView

0.42

 acquies

0.41

юнча

0.41

VSLU

0.41

icuous

0.39

Zespół

0.39

extré

0.39

ഭ്യാസ

0.39

POSITIVE LOGITS

 Simple

0.43

 Basic

0.42

 basic

0.40

 Public

0.39

 기본적인

0.39

 simple

0.38

 American

0.38

 Standard

0.38

 easy

0.38

 mini

0.38

Activations Density 0.355%