INDEX

Explanations

complex relationships, higher dimensions

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

 صغير

0.48

 صغيرة

0.44

 ಕಡಿಮೆ

0.44

Smaller

0.43

 pequeno

0.43

மின்

0.42

 unintentionally

0.42

 rövid

0.42

 unintentional

0.42

 قصير

0.41

POSITIVE LOGITS

复杂

1.24

复杂的

1.20

 complex

1.15

Complex

1.10

 complicated

1.06

complex

1.06

複雜

1.05

 Complex

1.04

複雑

1.02

 phức

0.98

Activations Density 0.025%