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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    chance
    -0.78
    haps
    -0.71
    bor
    -0.69
    lip
    -0.67
    pin
    -0.66
    pins
    -0.64
    ones
    -0.64
    oner
    -0.63
     quiet
    -0.63
    ilic
    -0.63
    POSITIVE LOGITS
    llah
    0.79
     Tail
    0.73
     IG
    0.69
     ALS
    0.65
     Airlines
    0.64
     Riy
    0.63
    raits
    0.63
    uay
    0.62
     Tycoon
    0.61
    riks
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.