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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    em
    1.07
    h
    1.04
    er
    0.96
    am
    0.96
    CET
    0.93
    a
    0.93
    EA
    0.90
    erin
    0.89
    DCT
    0.89
    o
    0.89
    POSITIVE LOGITS
     of
    1.66
     ofthe
    1.28
    ของ
    1.25
     của
    1.23
    ของการ
    1.20
     thereof
    1.02
     של
    1.00
    ผ้า
    0.99
    诒
    0.99
    of
    0.98
    Act Density 1.796%

    No Known Activations