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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Tail
    -0.07
     rotterdam
    -0.07
     cuc
    -0.06
     �
    -0.06
    跆
    -0.06
    开店
    -0.06
     applaud
    -0.06
    母
    -0.06
    ippines
    -0.06
     print
    -0.06
    POSITIVE LOGITS
     tower
    0.07
    athan
    0.07
    fruit
    0.07
    영상
    0.07
    Trou
    0.07
    erton
    0.07
    ürü
    0.06
     Geo
    0.06
     soothing
    0.06
    USTER
    0.06
    Act Density 0.003%

    No Known Activations