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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ✨
    0.85
     reimag
    0.79
     mindfulness
    0.79
     🎉
    0.78
    ⁤
    0.76
     crafting
    0.75
     Dzięki
    0.75
     🌱
    0.75
     nuanced
    0.73
     mẽ
    0.73
    POSITIVE LOGITS
    但是在
    0.87
    mbox
    0.82
    但是我
    0.77
    但是
    0.76
    沒有
    0.73
    に関して
    0.73
    鎗
    0.73
     policemen
    0.71
    newspaper
    0.71
    大部分
    0.70
    Act Density 0.081%

    No Known Activations