INDEX

Explanations

attire being worn

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

 clothing

1.37

 Clothing

1.34

 garments

1.33

Clothing

1.31

 garment

1.29

 jackets

1.26

 shirts

1.23

 शर्ट

1.21

 shirt

1.18

clothing

1.16

POSITIVE LOGITS

 sparkles

0.95

 sparkly

0.92

 inappropriate

0.87

 glitter

0.84

 sparkle

0.79

matching

0.78

 sequ

0.77

 matching

0.76

rat

0.75

 ridiculous

0.74

Activations Density 0.115%