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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    redit
    -0.77
    ontent
    -0.73
    cuts
    -0.64
    ilver
    -0.64
    urus
    -0.63
    edia
    -0.63
    eping
    -0.61
    ovie
    -0.61
    morrow
    -0.61
    igans
    -0.61
    POSITIVE LOGITS
    icken
    0.79
    ythm
    0.70
    ãĤ¹ãĥĪ
    0.68
     amen
    0.65
    uity
    0.65
     audible
    0.63
     Qur
    0.62
    ãĤ£
    0.62
    Ô
    0.61
     Abyssal
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.