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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -risk
    -0.08
    aid
    -0.07
    >();
    -0.07
     kla
    -0.07
     ByteBuffer
    -0.07
    ily
    -0.06
     buck
    -0.06
    gd
    -0.06
    mé
    -0.06
     unters
    -0.06
    POSITIVE LOGITS
    峨
    0.08
    desired
    0.07
    不定
    0.07
    chosen
    0.07
     Eğer
    0.07
    บาคาร
    0.07
    优越
    0.07
    _rotation
    0.07
    бр
    0.07
     مجل
    0.07
    Act Density 0.179%

    No Known Activations