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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    тов
    -0.08
    אים
    -0.07
    ument
    -0.07
     الحكومة
    -0.07
    kek
    -0.07
     kaufen
    -0.07
    ולוגיה
    -0.07
    erman
    -0.07
    Seleccion
    -0.07
    ыми
    -0.07
    POSITIVE LOGITS
    =c
    0.07
    <X
    0.07
     clf
    0.07
    青睐
    0.07
     ↵    ↵
    0.06
     flood
    0.06
    घ
    0.06
    過程中
    0.06
    途
    0.06
    😛
    0.06
    Act Density 0.082%

    No Known Activations