INDEX

Explanations

specific terms following

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

 sign

1.88

sign

1.50

Sign

1.50

 Sign

1.49

 signs

1.42

 signo

1.30

 signe

1.23

 знак

1.22

 signos

1.21

Signs

1.20

POSITIVE LOGITS

 information

0.53

 data

0.49

 информации

0.48

 信息

0.48

 데이터를

0.46

信息

0.46

 информацией

0.45

 informasi

0.45

 তথ্য

0.44

 информация

0.44

Activations Density 0.162%