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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    o
    1.27
    s
    1.24
    l
    1.22
    :
    1.17
     in
    1.16
    u
    1.11
    z
    1.05
    a
    1.05
    d
    1.04
    st
    1.01
    POSITIVE LOGITS
    。
    1.38
    ى
    1.20
    وم
    1.19
    )。
    1.17
    وس
    1.13
    ния
    1.12
    )，
    1.09
    ї
    1.09
    า
    1.08
    نا
    1.05
    Act Density 0.000%

    No Known Activations