INDEX

Explanations

legal citations and numbers

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

weakSelf

-1.94

 aprecia

-1.93

梱

-1.86

 persecu

-1.84

 revisa

-1.78

 ambayo

-1.76

 видимо

-1.76

槐

-1.73

 pierde

-1.71

 provoca

-1.70

POSITIVE LOGITS

the

2.48

nessy

2.41

.”

2.36

2.25

cellor

2.09

↵

2.06

śmy

2.05

></

2.03

 einem

2.03

</h3>

2.00

Activations Density 0.033%