INDEX

Explanations

module definition namespace

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

 élabor

-1.61

 voitures

-1.55

ÁRIO

-1.52

 laiss

-1.50

鱨

-1.49

齙

-1.43

 avions

-1.41

IVERSITY

-1.41

ния

-1.41

“

-1.38

POSITIVE LOGITS

to

2.00

 Cualquier

1.68

 Ellos

1.65

-¿

1.62

 adım

1.59

 during

1.59

 karşılaş

1.57

ור

1.56

了一会儿

1.56

 Hacer

1.53

Activations Density 0.018%