INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ς
    1.48
    ים
    1.39
    ی
    1.30
    s
    1.28
    ओं
    1.05
    dollars
    1.03
    ের
    0.98
    ни
    0.98
    demos
    0.96
    rockets
    0.96
    POSITIVE LOGITS
     of
    1.37
    t
    1.23
    '
    1.07
    .
    1.04
    то
    1.02
    0.99
    0.94
    ");
    0.93
    al
    0.90
    想起
    0.88
    Act Density 0.031%

    No Known Activations