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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -web
    -0.08
    奖学金
    -0.08
    _HOME
    -0.07
     champagne
    -0.07
     Workshop
    -0.07
    优惠
    -0.07
     influential
    -0.07
     çalıştı
    -0.07
    _dropout
    -0.07
    Execute
    -0.07
    POSITIVE LOGITS
    貝
    0.07
     fueron
    0.06
     ذات
    0.06
    Ո
    0.06
     Ve
    0.06
    ड
    0.06
    пов
    0.06
     Dut
    0.06
    proved
    0.06
     boasted
    0.06
    Act Density 0.033%

    No Known Activations