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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    i
    1.67
    or
    1.63
    et
    1.63
    ak
    1.62
    is
    1.52
    in
    1.52
    y
    1.51
    ou
    1.48
    al
    1.46
    an
    1.45
    POSITIVE LOGITS
     ساتھ
    1.02
     délais
    1.02
     tratamientos
    0.97
     cinética
    0.97
     год
    0.96
    ्‍यादा
    0.95
    期限
    0.95
     hidrógeno
    0.94
    醅
    0.94
    噻
    0.91
    Act Density 0.244%

    No Known Activations