INDEX

Explanations

concepts followed by related categories

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

 glorie

0.41

 монасты

0.40

 lush

0.40

နိုင်ငံ

0.40

鉗

0.40

 Wildlife

0.38

Deterministic

0.38

 作詞

0.38

Wildlife

0.38

loo

0.37

POSITIVE LOGITS

 following

0.36

ंत्रिक

0.33

下一

0.33

LFT

0.32

到底是

0.32

 Following

0.32

ージー

0.32

$<

0.31

uwe

0.30

 следу

0.30

Activations Density 0.208%