INDEX
    Explanations

    emotional expressions of love and devotion

    New Auto-Interp
    Negative Logits
     pivot
    -0.14
    abez
    -0.14
    formed
    -0.14
    blas
    -0.14
    ufe
    -0.13
    ipi
    -0.13
    endar
    -0.13
    ZE
    -0.13
     Gallup
    -0.13
    &);↵↵
    -0.13
    POSITIVE LOGITS
     shine
    0.32
     shines
    0.31
     Shine
    0.26
     shining
    0.24
     se
    0.24
     sh
    0.24
     comes
    0.23
     surface
    0.22
    shine
    0.22
     rear
    0.21
    Act Density 0.195%

    No Known Activations