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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     onAnimation
    -0.08
     WINDOW
    -0.07
     verm
    -0.07
     onPage
    -0.07
    toDate
    -0.07
     --------↵
    -0.07
     Aydın
    -0.07
    车上
    -0.07
     fix
    -0.07
    .setModel
    -0.07
    POSITIVE LOGITS
     truth
    0.10
     shortcomings
    0.08
    言えば
    0.08
     realidad
    0.08
     đổi
    0.08
    ではなく
    0.07
    悲哀
    0.07
     selves
    0.07
    贝尔
    0.07
    lijke
    0.07
    Act Density 0.010%

    No Known Activations