INDEX

Explanations

logarithm or log base

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

🌸

-1.73

dear

-1.50

“

-1.47

🙌

-1.45

⟦

-1.44

 verschillen

-1.41

狁

-1.38

 アンド

-1.37

💗

-1.36

🫶

-1.34

POSITIVE LOGITS

of

2.63

你也

1.83

 Speisen

1.80

1.79

苙

1.73

 duże

1.70

mathrm

1.69

 REALLY

1.68

 unbelievably

1.65

 einem

1.64

Activations Density 0.005%