INDEX

Explanations

parameters and technical details in a complex document

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Instagram

-0.07

 instagram

-0.07

engo

-0.07

 Disqus

-0.07

 Jenner

-0.07

/moment

-0.07

 whatsapp

-0.06

 Columns

-0.06

 WhatsApp

-0.06

uploader

-0.06

POSITIVE LOGITS

hyp

0.17

Hyp

0.14

 hyper

0.12

hyp

0.12

 Hyper

0.11

hyper

0.10

 hyperlink

0.10

 hypert

0.10

WWW

0.10

 document

0.10

Activations Density 0.023%