INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     étoient
    -0.91
     مرئيه
    -0.88
    ]--;
    -0.85
     avoient
    -0.84
     auroit
    -0.82
    AutoScaleMode
    -0.79
    $.
    
    -0.79
     jLabel
    -0.79
     feroit
    -0.78
    ftance
    -0.77
    POSITIVE LOGITS
    <bos>
    0.83
    .
    0.64
    A
    0.56
    ↵↵
    0.55
    I
    0.54
    1
    0.52
    0.52
     estimés
    0.51
    0.50
    <strong>
    0.49
    Act Density 0.286%

    No Known Activations