INDEX

Explanations

rooms with direct access

The neuron fires on numeric specifications in real-estate listings—measurements, counts, and other quantitative property details.

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

to

-2.14

 empiezan

-1.91

 they

-1.72

}$,

-1.70

他们的

-1.62

 ongeveer

-1.61

 auswählen

-1.60

 llegan

-1.59

 their

-1.57

 podrían

-1.56

POSITIVE LOGITS

 quartiers

1.55

Ď

1.45

こちらは

1.42

 postes

1.38

 another

1.38

În

1.37

 same

1.36

)();

1.34

恭喜

1.30

 collaborateurs

1.30

Activations Density 0.022%