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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -chief
    -0.08
     Sullivan
    -0.07
     обла
    -0.07
    שנתי
    -0.07
    _fake
    -0.07
    phis
    -0.07
    キャンペーン
    -0.07
    innacle
    -0.07
    upal
    -0.07
     phishing
    -0.07
    POSITIVE LOGITS
     #
    0.08
    kbd
    0.07
    铊
    0.07
     gem
    0.07
     //
    0.07
    信赖
    0.07
     time
    0.07
     takes
    0.07
     Ч
    0.07
     draw
    0.07
    Act Density 0.026%

    No Known Activations