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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arthed
    -0.85
     Reloaded
    -0.79
    anamo
    -0.69
     Fidel
    -0.66
    enhagen
    -0.66
     scrut
    -0.64
     Dek
    -0.61
    ruary
    -0.61
    eon
    -0.61
    BuyableInstoreAndOnline
    -0.60
    POSITIVE LOGITS
    boys
    0.77
    girls
    0.74
    女
    0.71
    ité
    0.70
    ipple
    0.70
    umbn
    0.69
    psc
    0.67
    boy
    0.66
    isations
    0.64
    )--
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.