INDEX
    Explanations

    topics related to fitness and exercise training

    New Auto-Interp
    Negative Logits
     sóng
    -0.15
     Bowman
    -0.15
     slashes
    -0.15
    ical
    -0.14
    iego
    -0.14
    ãĥ¼ãĥĢ
    -0.14
    ogra
    -0.14
    ambio
    -0.13
     Robertson
    -0.13
    technology
    -0.13
    POSITIVE LOGITS
     lift
    0.41
     lifting
    0.40
    lifting
    0.36
     lifts
    0.36
    lift
    0.36
     Lift
    0.35
     lifted
    0.30
     weights
    0.29
     lif
    0.28
     squat
    0.28
    Act Density 0.120%

    No Known Activations