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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    anus
    -0.76
    crop
    -0.74
    Poly
    -0.72
    hest
    -0.72
    birth
    -0.71
    quit
    -0.71
    âĵĺ
    -0.69
    born
    -0.68
     âĵĺ
    -0.67
    agn
    -0.65
    POSITIVE LOGITS
     Macy
    0.64
     Choi
    0.64
     Harvard
    0.63
     phr
    0.63
     Fargo
    0.63
     JPMorgan
    0.61
     JPM
    0.61
    strom
    0.61
    neapolis
    0.60
     Earn
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.