INDEX

Explanations

comparing apples and oranges

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

 Sensing

0.39

ව්

0.39

ぷ

0.37

 exhibits

0.37

 Affidavit

0.36

 Exhibit

0.36

震

0.35

 Lust

0.35

ު

0.35

 halde

0.34

POSITIVE LOGITS

 apples

1.77

apples

1.52

 Apples

1.41

 comparing

1.27

comparing

1.21

 apple

1.18

 comparisons

1.13

 comparar

1.10

苹果

1.09

 comparison

1.09

Activations Density 0.037%