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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Sov
    -0.77
    destruct
    -0.76
    nown
    -0.72
    pmwiki
    -0.70
    rez
    -0.69
    azi
    -0.69
    ainer
    -0.68
    Äĩ
    -0.67
    accompanied
    -0.67
    onna
    -0.66
    POSITIVE LOGITS
    Ĥ¬
    0.67
     Webb
    0.64
     Rez
    0.62
     Macy
    0.61
     Hodg
    0.61
     shopping
    0.61
     actionGroup
    0.60
     Shoot
    0.60
     Receiver
    0.60
    Alert
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.