INDEX

Explanations

passive voice markers

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

த்துள்ள

0.73

 kullanarak

0.72

ยังมี

0.71

 سمجھتے

0.64

 କରି

0.62

 جانتے

0.61

 रवाना

0.58

 eyeing

0.58

 falou

0.57

 Gibt

0.56

POSITIVE LOGITS

被

2.70

ถูก

2.52

被

2.42

 được

2.36

 ถูก

2.17

 worden

2.13

都被

2.11

会被

2.06

就被

2.03

而被

1.99

Activations Density 0.836%