INDEX

Explanations

qualifying uncertainty

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

What

-1.73

This

-1.72

數字

-1.66

Here

-1.64

他們的

-1.56

無論

-1.53

幾乎

-1.51

 künstler

-1.50

焄

-1.48

Let

-1.47

POSITIVE LOGITS

ческа

1.68

 messed

1.63

ünde

1.55

 Majesté

1.55

 camisa

1.45

िक

1.45

ție

1.44

 screwed

1.42

 hänen

1.39

 cámara

1.38

Activations Density 0.012%