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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     بعدها
    0.42
     pentru
    0.41
     afterwards
    0.41
     عند
    0.40
     після
    0.40
    으니
    0.40
     전체
    0.39
    进行了
    0.39
     للح
    0.38
    시는
    0.38
    POSITIVE LOGITS
     Sebab
    0.51
     sebab
    0.49
     jang
    0.48
     Wong
    0.47
     wong
    0.46
     chiave
    0.45
     Whether
    0.43
    Tapi
    0.43
     coba
    0.43
     Mak
    0.43
    Act Density 0.001%

    No Known Activations