INDEX

Explanations

of course

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

 δύο

0.57

 двох

0.56

 дори

0.53

 ಸುಮ

0.51

 pourtant

0.50

 навіть

0.50

虽

0.50

 প্রায়

0.50

 thậm

0.50

 dvě

0.48

POSITIVE LOGITS

 oczywiście

1.75

當然

1.59

当然

1.57

 ovviamente

1.56

 évidemment

1.52

 obviously

1.49

 natürlich

1.47

もちろん

1.45

 당연

1.41

 natuurlijk

1.36

Activations Density 0.360%