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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     -=
    -0.07
    zn
    -0.07
    VA
    -0.07
    exchange
    -0.06
     energ
    -0.06
    请你
    -0.06
    宝鸡
    -0.06
     Airlines
    -0.06
    ()),
    -0.06
     продукции
    -0.06
    POSITIVE LOGITS
    🥁
    0.07
     LOVE
    0.07
    ��
    0.07
    >Total
    0.07
    谑
    0.06
    曦
    0.06
     Colbert
    0.06
    绦
    0.06
    RAFT
    0.06
     Sand
    0.06
    Act Density 0.005%

    No Known Activations