INDEX

Explanations

identifying descriptive phrases

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

但

0.51

Aus

0.50

 trama

0.47

短暂

0.46

 लाहिड़ी

0.46

ління

0.45

 δο

0.45

എം

0.44

żenie

0.43

pan

0.43

POSITIVE LOGITS

 Presentations

0.46

 Tasty

0.43

 supermarkets

0.42

 diversified

0.42

 selectively

0.41

 toned

0.41

र्फ

0.41

ONE

0.41

 Connectivity

0.41

اکر

0.40

Activations Density 0.002%