INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    rawDesc
    -0.82
     myſelf
    -0.82
    ratulations
    -0.79
     himſelf
    -0.77
     neceff
    -0.76
     ſhould
    -0.75
     Jefus
    -0.74
     avoient
    -0.73
     feroit
    -0.73
    StoryboardSegue
    -0.73
    POSITIVE LOGITS
    ,
    0.88
    -
    0.83
    th
    0.74
    .
    0.66
    :
    0.66
    ;
    0.65
    /
    0.64
     utafitiHapana
    0.56
    (
    0.53
    adpleegd
    0.52
    Act Density 0.062%

    No Known Activations