INDEX

Explanations

distinct proper nouns

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

 first

1.71

First

1.56

first

1.54

 First

1.53

 FIRST

1.45

FIRST

1.43

 फर्स्ट

1.30

 første

1.27

 eerste

1.25

 första

1.21

POSITIVE LOGITS

Kalau

0.37

assertEqual

0.37

 வா

0.36

椏

0.36

ଅ

0.35

କୁ

0.35

 болот

0.34

ConformanceMode

0.34

azes

0.34

 outs

0.34

Activations Density 0.003%