INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ه
    -0.87
    o
    -0.80
    e
    -0.75
    a
    -0.75
    ی
    -0.71
    er
    -0.70
     “
    -0.70
    iak
    -0.69
    i
    -0.65
    y
    -0.61
    POSITIVE LOGITS
     Jefus
    1.24
     ſtate
    1.20
     greateſt
    1.20
     Monfieur
    1.20
     Diſ
    1.19
     Reſ
    1.16
     Efq
    1.16
     ſche
    1.14
     purpoſe
    1.14
     Majefty
    1.13
    Act Density 0.115%

    No Known Activations