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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Bes
    -0.07
     Bew
    -0.07
    -marker
    -0.07
    .setHorizontal
    -0.06
    -flight
    -0.06
    .Include
    -0.06
    สว
    -0.06
     dequeue
    -0.06
    矻
    -0.06
    \Backend
    -0.06
    POSITIVE LOGITS
    ā
    0.08
    =============↵
    0.08
    ヽ
    0.07
    舰队
    0.07
    油漆
    0.07
    alpha
    0.07
    职责
    0.07
     brushed
    0.06
    这种情况
    0.06
    Number
    0.06
    Act Density 0.021%

    No Known Activations