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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    guessing
    1.12
     Conjecture
    0.98
    (?)
    0.94
     stupid
    0.94
    thinking
    0.93
     Hume
    0.92
    chessboard
    0.92
     conjectures
    0.92
     beh
    0.92
    imgur
    0.91
    POSITIVE LOGITS
     بالإضافة
    1.28
     এন্ড
    1.12
     অ্যান্ড
    1.03
    沃
    1.01
     danh
    0.99
     प्लेटफॉर्म
    0.98
     đặc
    0.98
     điểm
    0.97
    ·
    0.96
     शामिल
    0.95
    Act Density 0.282%

    No Known Activations