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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     DEALINGS
    -0.07
     containerView
    -0.07
    领先的
    -0.07
     dream
    -0.07
    _Comm
    -0.07
    \App
    -0.07
    帏
    -0.07
     Trick
    -0.07
    _cap
    -0.07
     brick
    -0.06
    POSITIVE LOGITS
     mitig
    0.07
    량
    0.07
     paylaş
    0.07
    굴
    0.07
    肯定会
    0.07
    曌
    0.07
    ないこと
    0.07
    👊
    0.07
     الن
    0.07
    들
    0.06
    Act Density 0.077%

    No Known Activations