INDEX

Explanations

regions and areas

The neuron fires on words that name subdivided sections or areas (e.g. region, regions, parts, portions, areas).

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

and

-1.46

 inmiddels

-1.25

鲎

-1.23

obr

-1.20

xiaomi

-1.20

 zoeken

-1.18

 Ordem

-1.18

 leggera

-1.15

 salonu

-1.15

 zouden

-1.15

POSITIVE LOGITS

of

2.98

 areas

1.79

«

1.63

 area

1.60

 where

1.57

«

1.55

 sections

1.44

「

1.41

 часть

1.38

 portions

1.30

Activations Density 0.073%