INDEX

Explanations

mentions of Hong Kong and Cantonese culture

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

IVEREF

-0.56

ckså

-0.55

nesota

-0.55

 nyelv

-0.55

huy

-0.53

ineas

-0.53

 oreja

-0.53

ä

-0.52

nyv

-0.52

gü

-0.52

POSITIVE LOGITS

 Hong

1.51

 Hongkong

1.50

Hong

1.34

 KONG

1.23

 hong

1.19

 Kong

1.09

HK

1.09

Kong

1.01

 Cantonese

0.98

hk

0.94

Activations Density 0.006%