INDEX

Explanations

No Explanations Found

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

 ficou

0.51

एलबी

0.50

 Giáo

0.47

撅

0.47

 Creed

0.46

⛸

0.46

蕙

0.46

 योग

0.46

OrderFlight

0.45

🏳

0.45

POSITIVE LOGITS

 warnings

0.48

 infringing

0.45

 TOPS

0.45

 Stupid

0.45

 benchmarks

0.44

 murdering

0.44

ᒧ

0.43

なります

0.43

 fluctuation

0.42

 fortifications

0.41

Activations Density 0.000%

No Known Activations