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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Riy
    -0.71
    Īè
    -0.69
     invitations
    -0.65
     secret
    -0.62
     AQ
    -0.62
     resc
    -0.62
     extradition
    -0.61
     Nem
    -0.61
     Mush
    -0.61
     minorities
    -0.60
    POSITIVE LOGITS
    owment
    0.77
    cht
    0.77
    itness
    0.74
    otin
    0.72
    milo
    0.72
    chel
    0.71
    actory
    0.71
    upe
    0.70
    ocamp
    0.69
    ãĤ¼ãĤ¦ãĤ¹
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.