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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Mercer
    -0.07
     donors
    -0.07
    NFL
    -0.06
    bservable
    -0.06
    .onNext
    -0.06
     Skinny
    -0.06
    イヤ
    -0.06
    狄
    -0.06
    ဓ
    -0.06
     Fuel
    -0.06
    POSITIVE LOGITS
     rtl
    0.08
    cbc
    0.08
     rewrite
    0.07
    Ratio
    0.07
    ób
    0.07
    思想
    0.07
    的概率
    0.07
    𝓊
    0.06
    쟀
    0.06
    line
    0.06
    Act Density 0.018%

    No Known Activations