INDEX

Explanations

mentions of family relationships, particularly wives

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

 girl

-0.12

woman

-0.11

 woman

-0.11

 Women

-0.11

 Girl

-0.11

 Daughter

-0.11

 Girls

-0.11

 Woman

-0.11

 girls

-0.11

 female

-0.11

POSITIVE LOGITS

 Kelly

0.07

 Kerry

0.07

 Fallon

0.07

 Christ

0.06

Lar

0.06

Mon

0.06

 Tracy

0.06

Kr

0.06

Fel

0.06

 Christie

0.06

Activations Density 0.146%