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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lander
    -0.86
    obyl
    -0.78
    bye
    -0.76
    auer
    -0.76
    aughters
    -0.74
    wcs
    -0.73
     adolesc
    -0.72
    deen
    -0.72
    undai
    -0.71
    ais
    -0.71
    POSITIVE LOGITS
    aries
    0.75
     Nights
    0.64
     Bugs
    0.62
     Drops
    0.62
     Que
    0.62
     Coins
    0.61
     XCOM
    0.60
     Controlled
    0.60
     MAC
    0.59
     Poly
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.