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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lenient
    0.86
     incompar
    0.85
    o
    0.84
     migrant
    0.81
    ज
    0.77
     erythe
    0.77
    er
    0.75
     yên
    0.75
     arg
    0.73
     negligent
    0.73
    POSITIVE LOGITS
    های
    0.83
    ssä
    0.80
    ޓ
    0.79
    ها
    0.78
    llll
    0.75
    spy
    0.74
    carouselExample
    0.70
    saver
    0.70
    brellas
    0.68
    ski
    0.67
    Act Density 0.000%

    No Known Activations