INDEX

Explanations

references to significant topics or concepts related to societal issues

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

illet

-0.09

lei

-0.07

usk

-0.07

Äįel

-0.07

%E

-0.07

croft

-0.07

visa

-0.07

 konkrÃ©t

-0.07

istol

-0.07

itesse

-0.07

POSITIVE LOGITS

 entire

0.08

 skies

0.07

 otherwise

0.07

 proceedings

0.07

 scene

0.07

 space

0.07

 pages

0.07

otherwise

0.06

pages

0.06

 minds

0.06

Activations Density 0.035%