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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hearts
    -0.28
    etting
    -0.26
    ìĬ¬
    -0.26
    çIJ¨
    -0.26
    lep
    -0.26
    obuf
    -0.25
    OfWork
    -0.24
     banking
    -0.24
    ä¸įæ¸ħæ¥ļ
    -0.24
    itorio
    -0.24
    POSITIVE LOGITS
    yt
    0.29
    éģĵ
    0.29
    åģľ
    0.25
     personally
    0.25
    ä¸Ģç«Ļ
    0.25
    RS
    0.24
    缮æłĩ
    0.24
    åľ°ä¸Ń
    0.24
    个人
    0.24
    ÎĹ
    0.23
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.