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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    妲
    -0.07
    Proto
    -0.07
     advice
    -0.07
    egot
    -0.06
    erner
    -0.06
     보기
    -0.06
    cern
    -0.06
    쐬
    -0.06
     Greene
    -0.06
     peny
    -0.06
    POSITIVE LOGITS
    슬
    0.08
     forthcoming
    0.07
     tụ
    0.07
    烟花爆
    0.07
     существ
    0.06
    椎
    0.06
     الثلاث
    0.06
    城市
    0.06
    子孙
    0.06
    开关
    0.06
    Act Density 0.020%

    No Known Activations