INDEX
    Explanations

    exclamations like "oh" often combined with feelings or time related words

    New Auto-Interp
    Negative Logits
    <bos>
    -1.04
    ++
    
    -0.82
    Portály
    -0.81
    "},
    
    -0.79
    __":
    
    -0.72
    ^(@)
    -0.70
    μφωνα
    -0.69
    )");
    
    -0.69
    -0.68
    ".
    
    -0.67
    POSITIVE LOGITS
     prisonniers
    0.85
     supérieures
    0.73
    Gön
    0.70
     intelig
    0.66
     leden
    0.65
     blessés
    0.63
     vertes
    0.62
    MemoryWarning
    0.61
     visuales
    0.61
    Har
    0.61
    Act Density 2.569%

    No Known Activations