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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lict
    -0.71
    âĨij
    -0.69
    á¹
    -0.67
    baum
    -0.66
     Haj
    -0.65
    ãĥİ
    -0.61
    tails
    -0.60
    akura
    -0.60
    isner
    -0.60
    ij士
    -0.60
    POSITIVE LOGITS
     rig
    0.79
     enthusi
    0.76
    oslav
    0.71
    Sax
    0.68
    osc
    0.66
     challeng
    0.64
    wig
    0.63
    cap
    0.62
     Cart
    0.62
    ams
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.