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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Passenger
    -0.70
     Clicker
    -0.67
     Pref
    -0.65
     Unique
    -0.64
     Resp
    -0.64
     Surve
    -0.63
     Keen
    -0.63
     Secondary
    -0.62
     Ada
    -0.62
     Forever
    -0.62
    POSITIVE LOGITS
    jug
    0.90
    oshenko
    0.88
    iaz
    0.88
    boxing
    0.80
    zel
    0.76
    rys
    0.76
    rosis
    0.75
    oval
    0.73
    oday
    0.72
    iatrics
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.