INDEX

Explanations

complex or abstract concepts often linked to perception or interpretation

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

 Belgian

-0.08

amazon

-0.08

 Belg

-0.07

Ngh

-0.07

 Moscow

-0.07

 Duis

-0.07

Gh

-0.07

 amazon

-0.07

 Albany

-0.07

 Alger

-0.07

POSITIVE LOGITS

 Croatia

0.10

Ven

0.09

Ven

0.09

 Naples

0.08

 Croatian

0.08

 Venice

0.08

 Saras

0.08

 Florida

0.07

Florida

0.07

 Jacksonville

0.07

Activations Density 0.041%