INDEX

Explanations

geographical regions and areas

The neuron fires on multiword geopolitical or regional area names (e.g. “Soviet Union,” “Baltic states,” “Dallas/Fort Worth Metroplex,” “tri-state area,” etc.).

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

-1.88

 while

-1.81

 bēr

-1.58

it

-1.53

in

-1.41

on

-1.39

 each

-1.37

 because

-1.33

 bekom

-1.33

at

-1.32

POSITIVE LOGITS

𝐒

1.34

WEB

1.34

</strong>

1.32

𝐁

1.28

 dain

1.26

 принцип

1.22

незон

1.21

Ли

1.20

</b>

1.20

 jueves

1.19

Activations Density 0.058%