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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ยà¸ĩ
    -0.16
    виÑĩай
    -0.14
    éal
    -0.13
    ìĥĿëĭĺ
    -0.12
    ìĿ´ìħĺ
    -0.12
    ìłĦìĹIJ
    -0.11
    ảy
    -0.11
    oot
    -0.11
    ChangeEvent
    -0.11
     kendisine
    -0.11
    POSITIVE LOGITS
     that
    0.94
     THAT
    0.89
     That
    0.84
    That
    0.81
    that
    0.81
    	that
    0.71
    éĤ£
    0.70
    _that
    0.70
    éĤ£ä¸ª
    0.65
     thats
    0.65
    Act Density 2.655%

    No Known Activations