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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.75
    allery
    -0.71
    \":
    -0.66
    DonaldTrump
    -0.64
    aft
    -0.63
    alez
    -0.62
    ipeg
    -0.61
    OTE
    -0.60
    eker
    -0.60
    Morning
    -0.59
    POSITIVE LOGITS
     Alvin
    0.78
     Saga
    0.71
     Daryl
    0.70
     Marvin
    0.69
    antine
    0.68
     Ezekiel
    0.67
    meier
    0.66
    face
    0.66
    esome
    0.65
     Vance
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.