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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     alebo
    0.66
    㴼
    0.64
     અથવા
    0.61
     veya
    0.59
     sì
    0.59
     millió
    0.59
     或者
    0.57
     innymi
    0.56
    portál
    0.56
    建设
    0.55
    POSITIVE LOGITS
    an
    0.86
    t
    0.73
    s
    0.65
    n
    0.64
    ina
    0.59
    one
    0.57
    our
    0.54
    from
    0.54
    as
    0.53
    all
    0.53
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.