INDEX

Explanations

mathematical equations and code

New Auto-Interp

Configuration

Dataset (Dashboard)

Various

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 digitally

-0.08

 Pauline

-0.08

_gender

-0.08

nica

-0.08

 decimal

-0.08

 genders

-0.08

 gender

-0.08

Gender

-0.08

است

-0.08

Decimal

-0.08

POSITIVE LOGITS

 dominate

0.10

 worst

0.10

 heuristic

0.10

Worst

0.10

 Worst

0.10

 Estimates

0.09

 dominates

0.09

peb

0.09

/compiler

0.09

 estimates

0.09

Activations Density 0.011%