INDEX

Explanations

Washington and New York places

The neuron detects mentions of the place name “Washington.”

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

-1.57

-1.38

-1.35

-1.34

–

-1.30

 barcel

-1.27

-1.26

.,

-1.24

-1.23

POSITIVE LOGITS

 drugi

1.48

 sposob

1.30

 energii

1.29

 ozdob

1.29

ریب

1.27

 klubu

1.27

 hrab

1.24

fordern

1.23

 stanu

1.23

nicht

1.21

Activations Density 0.067%