INDEX

Explanations

special characters and punctuation

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

ñor

-1.67

浤

-1.52

''

-1.51

 onCreateView

-1.51

出了一

-1.45

凝土

-1.43

_;

-1.43

ciale

-1.41

 от

-1.40

zló

-1.39

POSITIVE LOGITS

these

1.65

 then

1.61

這些

1.60

Are

1.53

这些

1.50

鹇

1.45

 każ

1.44

1.41

Would

1.39

Let

1.35

Activations Density 0.053%