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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     webcam
    -0.65
    feed
    -0.63
     fertility
    -0.61
     trump
    -0.61
    plot
    -0.60
     births
    -0.60
     polling
    -0.60
    lot
    -0.60
     prog
    -0.60
    Center
    -0.58
    POSITIVE LOGITS
    rir
    0.78
    heimer
    0.77
     Lauderdale
    0.73
     Skydragon
    0.72
    ĸļ
    0.72
    姫
    0.71
     Baal
    0.70
    ZA
    0.70
     Lamar
    0.69
    qqa
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.