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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Chr
    -0.07
     hon
    -0.07
     -*-
    -0.07
    CardBody
    -0.07
     Oct
    -0.06
    赠
    -0.06
    aren
    -0.06
    Chr
    -0.06
    把自己的
    -0.06
     "[%
    -0.06
    POSITIVE LOGITS
    معال
    0.09
     mejores
    0.07
     frequency
    0.07
    车辆
    0.07
    �
    0.07
    严重的
    0.07
     disasters
    0.07
    设备
    0.07
     mudança
    0.07
     doom
    0.07
    Act Density 0.004%

    No Known Activations