INDEX

Explanations

wants to see or hear

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

-1.61

 there

-1.50

 extremamente

-1.43

 abstrato

-1.42

もお

-1.40

 Verpflichtung

-1.37

 gerekiyor

-1.36

 Betrag

-1.35

也非常

-1.34

 casada

-1.34

POSITIVE LOGITS

зывать

1.41

 which

1.38

ção

1.35

のは

1.31

[];

1.30

 individ

1.29

 devine

1.27

 jacques

1.26

нение

1.23

mentos

1.22

Activations Density 0.024%