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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (car
    -0.07
     Frm
    -0.07
    资深
    -0.07
    暑期
    -0.07
     applauded
    -0.07
     superclass
    -0.07
    인터
    -0.07
    壸
    -0.07
    WX
    -0.07
    不得不说
    -0.06
    POSITIVE LOGITS
    今天
    0.08
    𝘁
    0.07
    过硬
    0.07
    ܛ
    0.07
    ика
    0.06
    那个
    0.06
     fatal
    0.06
    止
    0.06
    இ
    0.06
     emergence
    0.06
    Act Density 0.087%

    No Known Activations