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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Numerous
    0.69
     unei
    0.66
     numerous
    0.66
     впоследствии
    0.66
     sejumlah
    0.63
     לא
    0.60
     seorang
    0.60
     avoids
    0.60
     dominated
    0.59
     predominantly
    0.59
    POSITIVE LOGITS
    细节
    1.09
    why
    1.05
    为什么
    1.05
     detalles
    1.05
    如何
    1.03
     details
    1.01
    details
    0.99
    importance
    0.99
    explanation
    0.98
    explain
    0.97
    Act Density 0.990%

    No Known Activations