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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    爷
    -0.07
    pred
    -0.07
     Abe
    -0.07
    雄
    -0.07
     barber
    -0.07
    rev
    -0.07
     box
    -0.07
    ome
    -0.07
     grouping
    -0.07
    잪
    -0.07
    POSITIVE LOGITS
    癍
    0.08
    🏳
    0.07
    篌
    0.07
    㨳
    0.07
    ﱰ
    0.07
     ?:
    0.07
     телеф
    0.07
    �
    0.07
    чная
    0.07
    ƞ
    0.07
    Act Density 0.052%

    No Known Activations