INDEX

Explanations

relatively simple or straightforward

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

しくは

1.78

 Hälfte

1.43

ilerden

1.39

 travaillons

1.38

最後まで

1.36

 czasie

1.33

 polov

1.32

 utilizzare

1.31

 fyra

1.30

いません

1.30

POSITIVE LOGITS

 sorta

1.95

 particular

1.95

휩

1.91

凭

1.89

 sidelines

1.89

ῆ

1.89

忽然

1.86

 typical

1.83

rul

1.83

 ryth

1.82

Activations Density 0.078%