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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tur
    1.23
    сы
    0.98
    sz
    0.92
    he
    0.88
    cie
    0.88
    {\
    0.87
    www
    0.87
    if
    0.87
    Ş
    0.84
    est
    0.84
    POSITIVE LOGITS
     atrocities
    1.80
     σχέ
    1.74
    푅
    1.68
    <unused318>
    1.68
    <unused1127>
    1.68
    <unused593>
    1.68
    <unused618>
    1.67
    <unused1666>
    1.67
    ➘
    1.67
     opération
    1.67
    Act Density 0.000%

    No Known Activations