INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .gc
    -0.07
     Mana
    -0.06
    (logits
    -0.06
     tel
    -0.06
    DataSource
    -0.06
     οποίο
    -0.06
    _hello
    -0.06
    -0.06
    oca
    -0.06
    <Token
    -0.06
    POSITIVE LOGITS
    ingroup
    0.07
    –↵↵
    0.06
     spoiler
    0.06
    ….↵↵
    0.06
    amount
    0.06
     invoices
    0.06
     trophies
    0.06
    ydro
    0.06
     overlooked
    0.06
    від
    0.06
    Act Density 0.046%

    No Known Activations