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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     patrons
    -0.07
     accommodate
    -0.07
        ↵↵↵
    -0.07
    Route
    -0.07
     edible
    -0.07
    免疫
    -0.07
    .READ
    -0.06
     Hend
    -0.06
    Cele
    -0.06
     repro
    -0.06
    POSITIVE LOGITS
    사
    0.07
     accordion
    0.07
    别人
    0.07
    makers
    0.07
     оригинал
    0.07
    ומים
    0.07
     нормальн
    0.07
    军
    0.07
    ɴ
    0.07
     Bakan
    0.07
    Act Density 0.016%

    No Known Activations