INDEX

Explanations

references to specific ethnicities or national identities

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

Yan

-0.08

 French

-0.07

acro

-0.06

sec

-0.06

 Beard

-0.06

 Canadian

-0.06

 Dane

-0.06

ences

-0.06

Fra

-0.06

 thereof

-0.06

POSITIVE LOGITS

ien

0.17

rien

0.12

gien

0.12

alien

0.11

lien

0.11

ischer

0.10

isch

0.10

auen

0.10

inen

0.09

iden

0.09

Activations Density 0.009%