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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rate
    -0.78
    igham
    -0.77
    unta
    -0.73
    --------------------------------------------------------
    -0.72
    hibit
    -0.70
    resy
    -0.70
    olphins
    -0.69
    Austral
    -0.68
    gam
    -0.67
    rared
    -0.67
    POSITIVE LOGITS
    aceutical
    0.66
    ãĥ
    0.64
    ãĤµ
    0.61
    åĭ
    0.61
     feder
    0.59
     lawy
    0.59
     Mich
    0.58
    ulous
    0.57
     melts
    0.57
     benefic
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.