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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    '
    1.93
    ل
    1.50
    the
    1.41
    0
    1.41
    3
    1.38
    u
    1.38
    4
    1.38
    an
    1.35
    The
    1.35
    8
    1.34
    POSITIVE LOGITS
     in
    1.29
     on
    1.13
     to
    1.09
    DBGPRINT
    1.09
    рка
    1.09
     and
    1.07
     for
    1.02
     রোহিঙ্গ
    1.02
    দম
    0.99
    0.97
    Act Density 0.000%

    No Known Activations