INDEX
    Explanations

    contractions and possessive forms of pronouns

    New Auto-Interp
    Negative Logits
    <bos>
    -1.40
    
    
    -1.10
    <?
    -1.08
    -1.05
     Messieurs
    -1.00
    /**
    -1.00
     hentai
    -0.98
    <?
    
    -0.95
     racon
    -0.92
    /*!
    
    -0.89
    POSITIVE LOGITS
    ()")
    0.72
    0.72
    '
    0.69
    mathrm
    0.65
    Einzelnachweise
    0.64
    */;
    0.63
    $'
    0.62
    s
    0.61
     =",
    0.60
    Collegamenti
    0.59
    Act Density 0.285%

    No Known Activations