INDEX

Explanations

contractions with personal pronouns

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

is

2.15

not

1.85

are

1.81

 heeft

1.46

 adalah

1.44

has

1.42

 isnt

1.36

是没有

1.31

 cannot

1.30

已经是

1.27

POSITIVE LOGITS

捎

1.75

τού

1.74

мо

1.68

 кров

1.67

 Разби

1.66

嚿

1.62

 строй

1.61

 NoContent

1.55

сно

1.54

Dok

1.54

Activations Density 1.023%