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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Mond
    -0.74
    cise
    -0.72
    CENT
    -0.71
    tainment
    -0.70
    orld
    -0.69
    arge
    -0.68
     Mash
    -0.67
    Fu
    -0.67
     Loving
    -0.65
    liter
    -0.64
    POSITIVE LOGITS
    sylv
    0.86
    yles
    0.85
    leneck
    0.81
    amins
    0.77
     polio
    0.72
     Pixie
    0.70
    hett
    0.70
    icter
    0.68
     silenced
    0.67
    aeper
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.