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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     الإمام
    -0.08
     smarter
    -0.07
     defendants
    -0.07
    往往会
    -0.06
     entreprises
    -0.06
     الدول
    -0.06
     Employee
    -0.06
    🅰
    -0.06
    Earlier
    -0.06
     AnyObject
    -0.06
    POSITIVE LOGITS
    踊
    0.08
     cruc
    0.07
     Tue
    0.07
    冲锋
    0.07
     실행
    0.07
    背景
    0.07
    pc
    0.07
     Ball
    0.07
     bast
    0.07
    Scripts
    0.07
    Act Density 0.174%

    No Known Activations