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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Doc
    -0.64
     Tent
    -0.60
    eday
    -0.59
     thereafter
    -0.59
     Atomic
    -0.59
    ennis
    -0.59
     Helpful
    -0.59
    edd
    -0.59
    GN
    -0.58
    ATURE
    -0.58
    POSITIVE LOGITS
    abad
    0.77
    raz
    0.72
    WIN
    0.68
    taboola
    0.64
     counterfeit
    0.63
    ueller
    0.63
     comparisons
    0.62
    abama
    0.62
    ifax
    0.61
    esta
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.