INDEX

Explanations

place names in India

The neuron fires on tokens that are part of named geographic locations (especially Indian place 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

Bayern

-1.50

-1.46

Surprisingly

-1.34

Rango

-1.33

 that

-1.32

-1.30

by

-1.28

and

-1.24

壓

-1.23

壩

-1.23

POSITIVE LOGITS

."

1.84

">(</

1.83

">)</

1.63

۠

1.58

 corações

1.56

鸝

1.54

StoryboardSegue

1.53

摀

1.52

 sejam

1.48

 homens

1.45

Activations Density 0.065%