INDEX

Explanations

refusing your request

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

ть

1.54

ர்

1.41

er

1.40

ου

1.33

ူ

1.30

ح

1.27

ာ

1.25

ী

1.24

ئة

1.24

િંગ

1.24

POSITIVE LOGITS

nya

1.89

 banget

1.85

 semoga

1.84

 sekarang

1.80

Hag

1.79

nt

1.78

rivation

1.75

 painstaking

1.71

ifício

1.70

 sederhana

1.70

Activations Density 0.532%