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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    azines
    -0.81
    amar
    -0.70
     depos
    -0.70
    mbuds
    -0.68
    anguages
    -0.67
    arers
    -0.66
    imar
    -0.65
    enth
    -0.64
    aste
    -0.64
    liest
    -0.64
    POSITIVE LOGITS
    090
    0.70
    çī
    0.67
     Ultron
    0.67
    Fu
    0.62
     Osiris
    0.60
     Hunt
    0.59
    masters
    0.58
    arms
    0.58
     breakdown
    0.57
     disobedience
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.