INDEX

Explanations

explicit terms or methods

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

↵↵

-1.88

-1.74

 soir

-1.69

︲

-1.62

蠓

-1.53

 avec

-1.52

 mere

-1.52

 obſ

-1.51

 achar

-1.50

ные

-1.49

POSITIVE LOGITS

//'

1.81

while

1.70

 個室

1.67

Preparación

1.66

ୈ

1.62

𖥦

1.61

嗬

1.56

värr

1.56

 drau

1.54

 炒め

1.52

Activations Density 0.020%