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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ᨬ
    -0.07
     נשמע
    -0.07
     Tensor
    -0.07
     Mineral
    -0.07
     Newspaper
    -0.07
     índice
    -0.06
    一般来说
    -0.06
    aviest
    -0.06
    Jessica
    -0.06
     thyroid
    -0.06
    POSITIVE LOGITS
    .findBy
    0.07
    结构调整
    0.07
     Sailor
    0.07
    ),
    0.07
     interviewed
    0.07
    带你
    0.06
    .ReadAll
    0.06
    stoi
    0.06
     thầy
    0.06
    新一轮
    0.06
    Act Density 0.081%

    No Known Activations