INDEX
    Explanations

    assertive statements and expressions of obligations or conditions

    Auxiliary verbs (would, should, has, did, are)

    New Auto-Interp
    Negative Logits
    "]);
    
    -1.35
    "],
    
    -1.33
    '],
    
    -1.28
    ")));
    
    -1.26
    "])
    
    -1.24
    "]));
    -1.22
    ")){
    
    -1.21
    '},
    
    -1.20
    ."));
    -1.19
    ()]);
    -1.18
    POSITIVE LOGITS
     despite
    0.79
     during
    0.76
     durante
    0.72
     grazie
    0.71
     when
    0.69
     throughout
    0.68
    despite
    0.68
     because
    0.67
     díky
    0.65
     until
    0.65
    Act Density 0.259%

    No Known Activations