INDEX

Explanations

file extensions or technical suffixes

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

or

0.76

 pinch

0.72

â

0.70

scratch

0.69

ese

0.69

ones

0.68

 Koss

0.68

 ladd

0.67

uns

0.67

tens

0.66

POSITIVE LOGITS

也

1.62

Museum

1.61

 كتساوي

1.59

También

1.58

Kemudian

1.56

Also

1.56

Cntr

1.55

 også

1.55

 moet

1.54

 Ibid

1.53

Activations Density 1.403%