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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Composer
    -0.08
     complement
    -0.07
    phe
    -0.07
     입장
    -0.07
    =_
    -0.06
    楯
    -0.06
    gregator
    -0.06
    殄
    -0.06
     respect
    -0.06
    tensor
    -0.06
    POSITIVE LOGITS
    alking
    0.08
     Ebola
    0.07
     )↵
    0.07
     kosher
    0.07
    DBus
    0.07
     yg
    0.07
    (AP
    0.07
    AGIC
    0.07
     غال
    0.06
     나라
    0.06
    Act Density 0.002%

    No Known Activations