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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    idian
    -0.85
    Reviewed
    -0.71
    stat
    -0.69
    ificant
    -0.69
    ieties
    -0.67
    esta
    -0.65
    arios
    -0.65
    Bey
    -0.65
     Tid
    -0.64
    trop
    -0.64
    POSITIVE LOGITS
     accommodation
    0.67
     outburst
    0.66
     deduction
    0.65
     vouchers
    0.62
     favour
    0.62
    è¦ļéĨĴ
    0.62
     ambulance
    0.60
     apartment
    0.60
     anger
    0.59
     invasion
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.