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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ickets
    -0.75
    abeth
    -0.67
     Fernand
    -0.65
     GOODMAN
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
    emis
    -0.63
     Nev
    -0.62
    ATURE
    -0.62
    icket
    -0.61
     Yak
    -0.61
    POSITIVE LOGITS
    pring
    0.77
     undone
    0.69
    olesterol
    0.65
    yrim
    0.65
    yg
    0.65
    iasco
    0.64
    poon
    0.62
    tg
    0.62
    poons
    0.61
    aign
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.