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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    as
    1.66
    et
    1.38
    ar
    1.23
    وم
    1.20
    un
    1.16
    st
    1.13
    4
    1.12
    for
    1.09
    an
    1.08
    id
    1.04
    POSITIVE LOGITS
    '
    1.23
    ס
    1.20
    ]
    1.17
     of
    1.12
     is
    1.10
    ال
    1.03
    מ
    1.03
    אן
    1.02
    ﾝ
    1.01
    یی
    1.00
    Act Density 0.000%

    No Known Activations