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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hợp
    -0.08
     совершенно
    -0.07
     전혀
    -0.07
    חלום
    -0.07
    經常
    -0.06
    (D
    -0.06
     Müslü
    -0.06
    實現
    -0.06
    .Active
    -0.06
    ╁
    -0.06
    POSITIVE LOGITS
     Westbrook
    0.07
    TabControl
    0.07
    posing
    0.07
    퍄
    0.07
    inton
    0.07
     movers
    0.07
    地产
    0.07
    тельных
    0.07
    延长
    0.07
    elines
    0.07
    Act Density 0.003%

    No Known Activations