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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    psie
    0.79
     oczywiście
    0.74
    ile
    0.72
    на
    0.71
     конечно
    0.69
    erina
    0.69
    ps
    0.67
    beep
    0.66
    !
    0.65
    BatchNorm
    0.64
    POSITIVE LOGITS
     incentiv
    0.84
    ਰ
    0.80
     سب
    0.77
     възможно
    0.77
    ísimo
    0.77
     atento
    0.76
    ب
    0.76
     campi
    0.75
    喧
    0.75
    던
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.