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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    igated
    -0.72
    llor
    -0.65
    aukee
    -0.62
     praise
    -0.62
    igating
    -0.61
     Attend
    -0.61
     rave
    -0.60
     OG
    -0.60
    imens
    -0.60
     attendance
    -0.59
    POSITIVE LOGITS
    flo
    0.88
    yip
    0.76
    ãĥ¼ãĥĨ
    0.71
    oro
    0.70
     vulner
    0.70
    rete
    0.69
    chan
    0.68
    orno
    0.67
    rep
    0.66
    emetery
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.