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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    '
    1.28
     as
    1.27
    s
    1.26
    ς
    1.16
     popped
    0.98
     जिसमें
    0.95
     a
    0.93
     ทั้ง
    0.93
     I
    0.91
    </h2>
    0.90
    POSITIVE LOGITS
    et
    2.00
    an
    1.93
    on
    1.73
    ش
    1.59
    त
    1.51
    та
    1.43
    ো
    1.43
    os
    1.39
    ن
    1.36
    ল
    1.34
    Act Density 0.000%

    No Known Activations