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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     vibe
    -0.07
     Cowboy
    -0.07
    Número
    -0.06
    됫
    -0.06
     amore
    -0.06
    more
    -0.06
    体育彩票
    -0.06
    떄
    -0.06
     ($('#
    -0.06
     simul
    -0.06
    POSITIVE LOGITS
     idx
    0.08
     joint
    0.07
     ري
    0.07
    _adj
    0.07
    _len
    0.07
    布鲁
    0.07
     structured
    0.07
     centralized
    0.07
    kp
    0.07
    INTEGER
    0.07
    Act Density 0.023%

    No Known Activations