INDEX

Explanations

python module imports

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

 chunks

1.90

ínű

1.80

嚿

1.77

 esetén

1.75

čius

1.74

čkom

1.73

 vět

1.73

 nélkül

1.71

 humankind

1.69

 doigts

1.68

POSITIVE LOGITS

 আসেন

1.45

漆

1.43

 للن

1.43

 मला

1.41

really

1.39

 Очень

1.38

入

1.37

 ون

1.36

 وير

1.36

 اخ

1.34

Activations Density 0.348%