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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gentlemen
    -0.07
    根本就不
    -0.07
    AAAA
    -0.07
    Toast
    -0.07
     dealt
    -0.07
    讶
    -0.06
     spontaneously
    -0.06
    .lista
    -0.06
    才可以
    -0.06
    严厉打击
    -0.06
    POSITIVE LOGITS
    Kİ
    0.08
    BK
    0.07
     managerial
    0.07
    ówki
    0.07
    马云
    0.07
    벰
    0.07
    quad
    0.07
    rzy
    0.07
    olicies
    0.07
     cylinder
    0.07
    Act Density 0.013%

    No Known Activations