INDEX

Explanations

place names ending in ad

This neuron activates on capitalized named entities—proper nouns like people’s names, places, organizations, and brand names.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

of

-1.75

-1.67

to

-1.57

都想

-1.53

 meestal

-1.53

 menangkap

-1.53

 vrijdag

-1.52

 zichzelf

-1.50

libros

-1.49

 samenwerking

-1.47

POSITIVE LOGITS

)):

1.62

تاح

1.62

}\]

1.59

 воспользоваться

1.54

1.53

__":

1.53

 because

1.52

 only

1.49

他的

1.48

kében

1.48

Activations Density 0.409%