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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    纣
    -0.07
    突发
    -0.07
     --------↵
    -0.07
    _js
    -0.06
    (win
    -0.06
    	bg
    -0.06
    暮
    -0.06
     rừng
    -0.06
    guide
    -0.06
     './../../
    -0.06
    POSITIVE LOGITS
    anggan
    0.07
    (Chat
    0.07
    ಮ
    0.07
    \C
    0.06
     reflected
    0.06
    送到
    0.06
    ちゃんと
    0.06
    حلة
    0.06
    appointment
    0.06
     appointment
    0.06
    Act Density 0.000%

    No Known Activations