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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    scope
    -0.70
    iew
    -0.69
    aghan
    -0.68
    mie
    -0.67
    oly
    -0.66
    aires
    -0.66
    igne
    -0.65
    Reference
    -0.62
     Results
    -0.62
    elect
    -0.61
    POSITIVE LOGITS
     pseudonym
    0.72
     tremend
    0.70
     corrid
    0.69
    sha
    0.67
    inoa
    0.67
     sizeable
    0.65
     irresist
    0.64
    erenn
    0.64
     triv
    0.64
     hefty
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.