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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aughters
    -0.70
     scraps
    -0.66
    uously
    -0.64
     compliments
    -0.64
     favors
    -0.63
     presses
    -0.60
    0010
    -0.59
     Centauri
    -0.59
     Shogun
    -0.59
     candles
    -0.59
    POSITIVE LOGITS
    TPS
    0.78
    Reviewer
    0.73
    ÃŃs
    0.72
    cephal
    0.72
    ieu
    0.67
     largeDownload
    0.67
    meric
    0.67
    ith
    0.67
    ox
    0.66
    emort
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.