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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ب
    1.09
    ле
    0.91
    人
    0.89
    न
    0.85
    ्स
    0.75
    ন
    0.71
    син
    0.71
    гда
    0.70
    י
    0.69
    цията
    0.68
    POSITIVE LOGITS
     estavam
    0.96
     состоялась
    0.88
     Están
    0.87
     estaban
    0.87
    なりません
    0.87
     estão
    0.85
    };
    0.84
     coche
    0.82
     estaba
    0.81
     Optimize
    0.81
    Act Density 0.002%

    No Known Activations