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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tanks
    -0.76
    stores
    -0.72
    smanship
    -0.71
    iuses
    -0.71
    uth
    -0.71
    vill
    -0.69
    ouls
    -0.68
     Os
    -0.67
     Hos
    -0.66
    gow
    -0.66
    POSITIVE LOGITS
    ãĥ¼ãĥ³
    0.78
     anten
    0.77
    evin
    0.77
    uber
    0.72
    FN
    0.71
    endez
    0.70
     propensity
    0.69
     unaccompanied
    0.69
    axter
    0.69
    pread
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.