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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nikov
    -0.70
    Stand
    -0.67
    Personal
    -0.66
    CAR
    -0.66
    Party
    -0.65
    HUD
    -0.64
    Redd
    -0.63
    Pac
    -0.62
     mayoral
    -0.62
    Palestinian
    -0.62
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.83
    acter
    0.79
    ategory
    0.75
    ulner
    0.70
     Howe
    0.69
    ãĤ®
    0.68
     Pwr
    0.67
    lihood
    0.64
    illy
    0.64
     ende
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.