INDEX
    Explanations

    expressions of love and emotional connections within relationships

    New Auto-Interp
    Negative Logits
    ascript
    -0.17
     bekl
    -0.15
    /generated
    -0.15
    коз
    -0.15
    ũi
    -0.14
    Opaque
    -0.14
    igy
    -0.14
    itler
    -0.14
    ften
    -0.14
    ivid
    -0.14
    POSITIVE LOGITS
     love
    0.87
     Love
    0.76
    love
    0.74
    Love
    0.71
     LOVE
    0.70
    æĦĽ
    0.63
     loves
    0.62
    çα
    0.62
     æĦĽ
    0.52
     Loves
    0.51
    Act Density 0.252%

    No Known Activations