INDEX

Explanations

the word "Arab," especially when pluralized or in certain phrases

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 estimés

-0.74

erno

-0.63

ه

-0.62

 Helios

-0.59

 mellitus

-0.58

 fileName

-0.57

woocommerce

-0.57

 Kassel

-0.56

en

-0.56

 صوتيه

-0.56

POSITIVE LOGITS

 Arabs

1.20

 Arab

1.19

Ara

1.16

Ara

1.15

Arab

1.13

 arab

1.11

 ARAB

1.07

arab

1.02

ARAB

1.02

ara

0.93

Activations Density 0.005%