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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .getWriter
    -0.07
     myths
    -0.07
     Pruitt
    -0.07
     Mitt
    -0.07
     Stone
    -0.07
    -packages
    -0.07
     Powers
    -0.07
     þ
    -0.06
     Blaze
    -0.06
    Bush
    -0.06
    POSITIVE LOGITS
     Länder
    0.07
    eren
    0.07
     `,
    0.07
    得很
    0.06
    닛
    0.06
    面孔
    0.06
    hell
    0.06
     kuruluş
    0.06
    丢了
    0.06
    黢
    0.06
    Act Density 0.001%

    No Known Activations