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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    숭
    -0.07
    scar
    -0.07
     check
    -0.07
    닜
    -0.07
     swap
    -0.07
    _suspend
    -0.06
    Focus
    -0.06
     text
    -0.06
    hole
    -0.06
    skip
    -0.06
    POSITIVE LOGITS
    .runners
    0.07
     dreams
    0.07
     legalized
    0.07
    Ultimately
    0.07
     paved
    0.07
    Ŷ
    0.07
     goalkeeper
    0.07
     quaint
    0.07
    会影响到
    0.07
    <Scalars
    0.07
    Act Density 0.023%

    No Known Activations