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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    '
    0.56
     ነበር
    0.55
    the
    0.50
     porque
    0.50
     জনের
    0.48
    iong
    0.48
    ’
    0.48
    它
    0.47
    out
    0.47
     ponieważ
    0.47
    POSITIVE LOGITS
    خ
    0.60
    ح
    0.55
     amelyet
    0.51
    をと
    0.50
    স
    0.50
    مج
    0.49
     effectuer
    0.48
     JBL
    0.48
    كت
    0.48
    حي
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.