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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (dir
    -0.08
    棼
    -0.07
    🧲
    -0.07
    .TabPage
    -0.07
    Scale
    -0.07
    upy
    -0.07
     risen
    -0.07
    的趋势
    -0.07
    🦑
    -0.07
     Debate
    -0.07
    POSITIVE LOGITS
    Pod
    0.08
    序
    0.07
    -series
    0.07
    接近
    0.07
     thấp
    0.07
     proceeds
    0.07
    rece
    0.07
    ORDER
    0.07
    memo
    0.07
    emos
    0.07
    Act Density 0.105%

    No Known Activations