INDEX

Explanations

GitHub repository links

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

Screw

0.42

 становятся

0.41

<unused54>

0.40

陶瓷

0.40

 cushioning

0.39

 zoned

0.38

 می‌شوند

0.38

鶯

0.38

फाइनल

0.38

 సన్నివేశ

0.38

POSITIVE LOGITS

 GitHub

2.53

 github

2.52

github

2.41

GitHub

2.38

 Github

2.33

Github

2.20

GITHUB

1.73

 repo

1.56

 repos

1.34

 Repo

1.32

Activations Density 0.018%