INDEX

Explanations

## headings

This neuron detects second-level section headings, i.e. H2 tags or their Markdown equivalents.

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

panjang

-1.68

 Läs

-1.64

Fußball

-1.64

 ingrained

-1.63

 krás

-1.60

籥

-1.57

Legende

-1.57

 detaylı

-1.54

 září

-1.53

 autobús

-1.52

POSITIVE LOGITS

of

1.97

1.92

ing

1.80

ys

1.64

ere

1.64

in

1.63

鹇

1.61

").

1.61

iner

1.59

Activations Density 0.003%