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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     a
    0.55
     that
    0.55
     to
    0.54
     with
    0.53
     or
    0.53
     the
    0.51
    ات
    0.49
     when
    0.49
     in
    0.48
     from
    0.48
    POSITIVE LOGITS
    もちろん
    0.52
    horas
    0.49
    er
    0.48
    또한
    0.48
    ↵
    0.47
    нибудь
    0.47
     גם
    0.46
     odpowiedzial
    0.46
    뿐
    0.45
     zostanie
    0.44
    Act Density 0.000%

    No Known Activations