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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     loves
    -0.07
    ContextMenu
    -0.06
     suspense
    -0.06
    付出
    -0.06
    .google
    -0.06
    _DA
    -0.06
    戾
    -0.06
     Petroleum
    -0.06
    热度
    -0.06
     brunette
    -0.06
    POSITIVE LOGITS
     interactive
    0.07
    uku
    0.07
    ]]
    0.07
    _dispatcher
    0.06
     접
    0.06
    occupation
    0.06
    ゔ
    0.06
     כבר
    0.06
    دراسة
    0.06
    大豆
    0.06
    Act Density 0.004%

    No Known Activations