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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cca
    -0.82
    zee
    -0.74
    isha
    -0.72
    scene
    -0.70
    enko
    -0.69
    xy
    -0.64
    oya
    -0.63
     START
    -0.61
    initions
    -0.60
    rica
    -0.60
    POSITIVE LOGITS
     fielder
    0.70
    ãĤ´ãĥ³
    0.69
     exch
    0.66
     redes
    0.63
    reditary
    0.63
    ür
    0.63
     Gaal
    0.62
     Aval
    0.62
    bol
    0.61
     ÏĦ
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.