INDEX

Explanations

This neuron activates on code identifiers (especially in package or import paths) that name software‐architecture layers or component types, such as service, mapper, dao, model, configuration, api, ui, etc.

package 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

 verschied

-1.30

 myriad

-1.30

 estratégia

-1.23

 assorted

-1.22

 ähnliche

-1.21

 immense

-1.17

 reichlich

-1.16

 inscrição

-1.16

 verschieden

-1.16

 exceedingly

-1.16

POSITIVE LOGITS

and

2.11

 vestidos

1.34

鞴

1.33

 UITableViewCell

1.33

 janu

1.29

izados

1.28

zaamheid

1.27

 jaunes

1.24

»;

1.23

 cortinas

1.23

Activations Density 0.011%