INDEX
    Explanations

    conjunctions and transitional phrases that indicate causality or reasoning

    New Auto-Interp
    Negative Logits
     الحره
    -0.74
     myſelf
    -0.73
     itſelf
    -0.73
    expandindo
    -0.72
     ſeveral
    -0.72
     الدولى
    -0.71
     himſelf
    -0.71
    ſelf
    -0.71
     leſs
    -0.69
    ſelves
    -0.69
    POSITIVE LOGITS
     they
    0.87
     it
    0.79
     there
    0.78
    since
    0.77
     since
    0.76
     because
    0.75
    because
    0.70
     although
    0.69
    畢竟
    0.69
     we
    0.66
    Act Density 0.247%

    No Known Activations