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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Morph
    -0.07
     biz
    -0.07
     Fem
    -0.07
     hypers
    -0.07
    商人
    -0.06
    �
    -0.06
    �
    -0.06
    sciously
    -0.06
     converter
    -0.06
    _dict
    -0.06
    POSITIVE LOGITS
    מיקום
    0.07
    갔
    0.07
    离开
    0.07
     Castillo
    0.07
    쮮
    0.07
     García
    0.07
    zeń
    0.07
    ItemId
    0.07
     toda
    0.07
    ẩ
    0.07
    Act Density 0.004%

    No Known Activations