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

    Neuronpedia

    INDEX
    Explanations

    references to buildings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     kebun
    -0.67
    Исто
    -0.59
    stash
    -0.57
     Chad
    -0.56
     cote
    -0.55
     Vita
    -0.54
     stash
    -0.54
     busted
    -0.54
    clu
    -0.54
     potranno
    -0.54
    POSITIVE LOGITS
    Buildings
    1.01
     Buildings
    0.93
    تقاوى
    0.93
    RectangleBorder
    0.89
     buildings
    0.87
    buildings
    0.82
     BUILDINGS
    0.80
     skyscraper
    0.78
    loài
    0.78
     Autorizaciones
    0.77
    Act Density 0.006%

    No Known Activations