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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    成都
    -0.07
    腐败
    -0.06
    )o
    -0.06
    THEN
    -0.06
     Once
    -0.06
    _GOOD
    -0.06
     cadre
    -0.06
    €
    -0.06
     Traff
    -0.06
    齑
    -0.06
    POSITIVE LOGITS
    озв
    0.08
    ходят
    0.07
     לשמ
    0.07
    �
    0.07
    让消费者
    0.07
    xfb
    0.07
     pleasing
    0.07
    -registration
    0.07
     incentiv
    0.07
     simplicity
    0.07
    Act Density 0.009%

    No Known Activations