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

    Neuronpedia

    INDEX
    Explanations

    features related to windows and natural light in architectural descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.69
     sadar
    -0.64
    ⓧ
    -0.62
     Rasa
    -0.62
    NameInMap
    -0.60
    auté
    -0.57
     createState
    -0.56
    InitStruct
    -0.55
     Himo
    -0.54
    uteurs
    -0.54
    POSITIVE LOGITS
     windows
    0.82
     window
    0.80
     jendela
    0.73
    窗
    0.70
    window
    0.69
     窗
    0.68
     finestra
    0.64
     Fenster
    0.64
     fenêtres
    0.62
     Window
    0.61
    Act Density 0.078%

    No Known Activations