INDEX

Explanations

special characters and formatting in text

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mandela

-0.06

 Rodgers

-0.06

 Apollo

-0.06

 Mozart

-0.06

 Rolex

-0.06

 Nobel

-0.06

 Airbus

-0.06

 Winner

-0.06

BMW

-0.06

 Music

-0.06

POSITIVE LOGITS

 hardcore

0.11

 Hardcore

0.11

 Dust

0.11

 punk

0.10

punk

0.10

 Fucked

0.09

 Sick

0.09

dust

0.09

Trash

0.09

 Trash

0.08

Activations Density 0.004%