INDEX

Explanations

one followed by noun

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

-1.95

 endast

-1.45

Enllaces

-1.41

-1.34

เพียง

-1.32

 uniquement

-1.23

 justru

-1.20

and

-1.17

 simplement

-1.16

 pierwszej

-1.16

POSITIVE LOGITS

 that

2.00

 this

1.86

 such

1.44

として

1.39

 membuat

1.37

пят

1.35

ógico

1.35

 verheiratet

1.32

}$)

1.32

ámica

1.30

Activations Density 0.419%