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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ed
    -0.08
    加热
    -0.07
     When
    -0.07
    带领
    -0.07
    ))*
    -0.07
     discern
    -0.07
    铩
    -0.07
     possess
    -0.07
    )'↵
    -0.07
    楒
    -0.07
    POSITIVE LOGITS
    .Virtual
    0.07
    lords
    0.07
    aar
    0.07
     droit
    0.07
    Pago
    0.07
     konuşma
    0.07
    斯顿
    0.07
     Angels
    0.06
    ꞊
    0.06
    (layout
    0.06
    Act Density 0.003%

    No Known Activations