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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oreal
    -0.80
     improvised
    -0.77
    atti
    -0.72
    ternity
    -0.71
    orrow
    -0.70
    ¶æ
    -0.70
    DoS
    -0.69
     experien
    -0.69
    ä½ľ
    -0.67
    Rated
    -0.66
    POSITIVE LOGITS
     ILCS
    0.72
     Kut
    0.69
    cour
    0.68
     Generation
    0.65
     Belg
    0.65
     Chev
    0.63
    oak
    0.63
     Bund
    0.63
    lux
    0.62
     wards
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.