INDEX

Explanations

article followed by noun

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

谖

-2.52

 всё

-2.22

訫

-2.14

 ส์

-2.00

 Aufenthal

-1.98

 autorizado

-1.95

鹋

-1.93

 encontrada

-1.91

</h3>

-1.90

 многие

-1.88

POSITIVE LOGITS

滏

1.95



1.83

 vader

1.70

 Those

1.69

￠

1.62

 potensi

1.61

 kjer

1.53

 teknologi

1.53

1.52

 kommunik

1.51

Activations Density 0.001%