INDEX

Explanations

discussions about gender dynamics and disparities

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Negative Logits

jev

-0.08

andon

-0.07

utura

-0.07

jec

-0.07

(OS

-0.07

upa

-0.07

Ø§ÙĨØ³

-0.07

dle

-0.06

edly

-0.06

onse

-0.06

POSITIVE LOGITS

 gender

0.09

 genders

0.07

folk

0.07

 Gender

0.07

gender

0.07

kind

0.06

 DBNull

0.06

-heavy

0.06

/grpc

0.06

-only

0.06

Activations Density 0.019%

No Known Activations