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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    WHO
    -0.77
    å¼
    -0.74
    DEM
    -0.74
    ashtra
    -0.69
    TO
    -0.69
    proxy
    -0.68
    SE
    -0.68
    Sea
    -0.67
    BuyableInstoreAndOnline
    -0.67
    Ocean
    -0.67
    POSITIVE LOGITS
     Chao
    0.69
     Luck
    0.67
    ierrez
    0.67
    onies
    0.66
     Sims
    0.65
     Coliseum
    0.64
     luck
    0.63
     Bulldogs
    0.61
     Fei
    0.61
     Floyd
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.