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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Carney
    -0.70
     Claus
    -0.56
     Operator
    -0.56
     Quinn
    -0.55
     Ahmed
    -0.55
    mouth
    -0.54
    é¾į
    -0.54
     Ms
    -0.53
     Ahmad
    -0.53
    LINE
    -0.53
    POSITIVE LOGITS
    rum
    0.72
    ork
    0.69
    awei
    0.67
    hedon
    0.67
     Sorce
    0.66
    zsche
    0.64
    izoph
    0.64
    abwe
    0.63
    assic
    0.62
    lux
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.