INDEX
    Explanations

    expressions of feeling and emotion

    New Auto-Interp
    Negative Logits
     houſe
    -0.66
    ágenes
    -0.66
     HasFactory
    -0.63
    -0.62
    nezeu
    -0.62
     erſt
    -0.61
     ainfi
    -0.60
    ſcher
    -0.59
    wiſe
    -0.59
    veien
    -0.57
    POSITIVE LOGITS
     feel
    1.42
     FEEL
    1.38
     feeling
    1.38
     Feeling
    1.37
     Feel
    1.35
    Feel
    1.34
     feels
    1.31
    Feeling
    1.27
    feel
    1.27
     felt
    1.23
    Act Density 0.020%

    No Known Activations