INDEX

Explanations

author, authorship, author's

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

이드

0.48

ダイ

0.46

ง

0.45

使用者

0.44

ت

0.43

 사용자

0.42

ができる

0.42

 conditioners

0.42

الح

0.41

 utilizzo

0.41

POSITIVE LOGITS

 authors

1.00

 Authors

0.99

 author

0.94

 Author

0.94

author

0.91

 автор

0.88

Author

0.86

Authors

0.83

authors

0.82

 authorship

0.81

Activations Density 0.004%