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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     auto
    0.47
    auto
    0.44
     automaty
    0.42
     automatically
    0.41
     Auto
    0.41
    Auto
    0.40
     automático
    0.40
     Roofing
    0.40
    갱
    0.40
     automatic
    0.39
    POSITIVE LOGITS
    ocos
    0.46
    edizione
    0.38
     technically
    0.38
    ся
    0.37
     settimane
    0.37
    boxylate
    0.36
    ালী
    0.36
     dữ
    0.36
     vải
    0.36
     வய
    0.36
    Act Density 0.001%

    No Known Activations