INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    0.62
    ر
    0.60
    b
    0.59
    g
    0.55
    et
    0.54
    er
    0.51
    0.48
    d
    0.47
     seagulls
    0.45
    د
    0.45
    POSITIVE LOGITS
     I
    0.62
    I
    0.62
    -
    0.52
     A
    0.51
    \
    0.48
    ?
    0.46
    _
    0.45
     همچنین
    0.45
     putea
    0.44
    ası
    0.44
    Act Density 0.430%

    No Known Activations