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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    etown
    0.86
     capitaine
    0.82
     racers
    0.82
    crafted
    0.80
     warriors
    0.80
    udah
    0.79
    nicht
    0.79
     bauen
    0.79
    china
    0.78
     udah
    0.77
    POSITIVE LOGITS
    ):
    0.85
     различные
    0.81
    ())
    0.76
    いろんな
    0.75
    ()).
    0.74
    );
    0.73
     *)
    0.73
    )$;
    0.70
     ):
    0.69
    )$.
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.