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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Bundy
    -0.81
    ãĥīãĥ©ãĤ´ãĥ³
    -0.70
    DERR
    -0.69
     Henderson
    -0.67
     Mahar
    -0.65
    mc
    -0.64
     sag
    -0.62
     Kush
    -0.62
     Lav
    -0.62
     Neph
    -0.62
    POSITIVE LOGITS
    ilage
    0.73
    æ°
    0.72
    å°Ĩ
    0.72
    士
    0.67
    icular
    0.67
    icularly
    0.66
    Ĥİ
    0.66
    åľ
    0.65
    ifications
    0.61
    .>>
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.