Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    textual details related to buildings and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information related to skyscrapers and their architectural details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    buildings, rooms, elevators, tenants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     castles
    -0.59
    tagHelperRunner
    -0.58
     castle
    -0.58
     Häuser
    -0.57
     forts
    -0.55
    Castle
    -0.53
     Castle
    -0.52
     domicili
    -0.51
     CASTLE
    -0.50
     casa
    -0.50
    POSITIVE LOGITS
     tenants
    1.09
     tenant
    0.93
     elevators
    0.88
     elevator
    0.81
     Tenants
    0.78
     rooms
    0.71
     rooftop
    0.70
     negozi
    0.68
     EconPapers
    0.67
     escal
    0.67
    Act Density 0.156%

    No Known Activations