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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     and
    1.45
    ب
    1.20
    ll
    1.06
    هم
    1.02
     or
    1.00
     i
    0.94
    k
    0.91
    H
    0.91
    হ
    0.90
    </h2>
    0.88
    POSITIVE LOGITS
    ва
    1.17
    ра
    1.09
    то
    1.02
    ай
    0.96
    at
    0.94
     sported
    0.92
    ur
    0.89
    ала
    0.88
    ла
    0.87
     bygone
    0.87
    Act Density 0.000%

    No Known Activations