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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     traged
    -0.77
    merce
    -0.76
    ]),
    -0.74
    hib
    -0.73
    rette
    -0.71
    escription
    -0.69
    onen
    -0.68
    olphin
    -0.67
    ļéĨĴ
    -0.67
     untreated
    -0.66
    POSITIVE LOGITS
    天
    0.71
    igans
    0.71
    Writing
    0.65
    Bir
    0.63
     tempted
    0.62
     overw
    0.61
    女
    0.61
     adultery
    0.61
     appe
    0.60
    wolf
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.