INDEX
    Explanations

    phrases or sentences that discuss emotional or psychological struggles

    New Auto-Interp
    Negative Logits
     yet
    -0.17
    orthy
    -0.15
    ucas
    -0.15
    isti
    -0.15
    illes
    -0.14
    yet
    -0.14
    ustin
    -0.14
     Yet
    -0.14
    lei
    -0.13
    ilk
    -0.13
    POSITIVE LOGITS
     though
    0.18
     although
    0.18
    although
    0.17
    though
    0.17
    oldur
    0.17
     because
    0.16
    Though
    0.15
    because
    0.15
    dit
    0.15
     dun
    0.14
    Act Density 0.308%

    No Known Activations