INDEX

Explanations

punctuation

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.58

@"/

-0.50

 développe

-0.37

出版年

-0.33

vironment

-0.32

番

-0.32

 spacy

-0.32

 ambiente

-0.32

 fortsätter

-0.32

Embeddable

-0.32

POSITIVE LOGITS

windowFixed

0.76

 Wiktionnaire

0.74

存于互联网档案馆

0.72

#+#

0.69

 незавершена

0.68

 Monarchy

0.68

 utafitiHapana

0.67

marshaller

0.67

kuuta

0.66

ValueStyle

0.65

Activations Density 0.010%