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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Salem
    -0.69
     Xiao
    -0.67
     Asheville
    -0.67
     Sochi
    -0.65
     Savage
    -0.64
     evils
    -0.64
     Siege
    -0.64
     Hai
    -0.63
     Kiev
    -0.63
    mur
    -0.62
    POSITIVE LOGITS
    ouch
    0.81
    ĸļ
    0.77
    audi
    0.72
    */(
    0.69
    elle
    0.68
    fman
    0.68
    ouf
    0.68
    STR
    0.67
    alys
    0.66
    yden
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.