INDEX
    Explanations

    punctuation marks, specifically commas, indicating pauses or list separations in text

    Punctuation followed by discourse markers

    conjunctions introducing clauses

    New Auto-Interp
    Negative Logits
    }";
    -0.66
    ])){
    -0.64
    "}";
    -0.64
    }`;
    -0.61
    }');
    -0.59
    >");
    -0.55
    ()];
    -0.55
    )');
    -0.54
    `;
    
    -0.54
    >";
    
    -0.54
    POSITIVE LOGITS
     unlike
    0.79
     although
    0.74
     parado
    0.70
     indeed
    0.68
    tichetta
    0.64
     withal
    0.63
     fortunately
    0.63
     faute
    0.63
     besides
    0.62
     кроме
    0.62
    Act Density 0.116%

    No Known Activations