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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ãĥ
    -0.69
    izations
    -0.64
    èª
    -0.64
    éĽ
    -0.63
     hypot
    -0.62
    tumblr
    -0.62
    etsk
    -0.61
    acity
    -0.60
    apper
    -0.60
    width
    -0.59
    POSITIVE LOGITS
    rozen
    0.65
    enged
    0.61
    bage
    0.61
     grou
    0.59
     rounding
    0.59
    awed
    0.58
    bytes
    0.57
     rele
    0.57
     Shape
    0.57
     sealed
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.