INDEX

Explanations

exploit, abuse or endanger

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

पटॉप

0.39

ഗ്രഹം

0.39

azaar

0.39

annels

0.36

ंसद

0.35

ڄ

0.34

ambahan

0.34

ẍ

0.34

amot

0.34

itri

0.34

POSITIVE LOGITS

ful

1.29

istic

1.27

त्मक

1.17

的な

1.14

ային

1.14

적인

1.13

lijke

1.05

FUL

1.05

पूर्ण

1.03

aceous

1.01

Activations Density 0.045%