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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    izioni
    1.00
    ко
    0.92
     zwią
    0.89
    един
    0.89
    dete
    0.87
    )&=
    0.86
    ete
    0.86
    ommen
    0.85
    də
    0.82
    ент
    0.82
    POSITIVE LOGITS
     in
    1.71
    ?
    1.41
    s
    1.35
     در
    1.24
    在
    1.16
    ール
    1.06
    !
    1.06
     an
    1.02
    사
    1.00
     at
    0.96
    Act Density 0.000%

    No Known Activations