special characters or symbols that might represent specific concepts or entities

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

-0.09

-0.07

-0.06

 precip

-0.06

 chart

-0.06

 augment

-0.06

 augmented

-0.06

POSITIVE LOGITS

India

0.14

 Ellie

0.14

 India

0.14

 india

0.13

 Indi

0.13

 Backpack

0.12

Ell

0.11

 backpack

0.11

Ell

0.11

 Elli

0.11

Activations Density 0.002%