INDEX

Explanations

magician, Svetlana, horsemen, Russian and Chinese words

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

 andere

-2.72

✴

-2.69

ᝢ

-2.64

 شیپور

-2.52

 remnants

-2.44

 היה

-2.42

⤿

-2.42

虓

-2.41

臜

-2.41

杙

-2.39

POSITIVE LOGITS

2.98

was

2.95

 have

2.89

Now

2.45

,’

2.44

and

2.38

But

2.30

<em>

2.27

an

2.22

We

2.17

Activations Density 0.001%