INDEX

Explanations

warm and lush

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

 която

-1.50

 geweldig

-1.46

 básicamente

-1.41

niña

-1.38

estaba

-1.36

וּ

-1.31

éget

-1.30

 великолеп

-1.29

 verfügen

-1.27

谙

-1.27

POSITIVE LOGITS

 растения

1.33

ׇ

1.30

 молока

1.30

 τὴν

1.27

 mesmas

1.26

 τοῦ

1.23

idk

1.21

なんて

1.18

 façade

1.17

 вещества

1.16

Activations Density 0.058%