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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (
    1.30
     is
    1.29
    ’
    1.28
    א
    1.16
    ij
    1.13
    ط
    1.13
    وف
    1.11
    "
    1.09
    Lr
    1.08
    _
    1.07
    POSITIVE LOGITS
    ו
    1.37
    o
    1.31
    ם
    1.29
    i
    1.26
    the
    1.09
    in
    1.06
    ский
    1.02
    י
    1.02
    не
    0.98
    ри
    0.97
    Act Density 0.000%

    No Known Activations