INDEX
    Explanations

    phrases that express emotional depth or intensity

    New Auto-Interp
    Negative Logits
    -best
    -0.18
     mejores
    -0.18
    æľĢä½³
    -0.18
    (best
    -0.17
     meilleur
    -0.16
     best
    -0.15
    best
    -0.15
     finest
    -0.15
    imary
    -0.14
    nier
    -0.14
    POSITIVE LOGITS
     attached
    0.22
     impressed
    0.21
     alike
    0.19
     invested
    0.19
     pleased
    0.19
     few
    0.19
     relieved
    0.19
     thankful
    0.19
     quickly
    0.18
     differently
    0.18
    Act Density 0.067%

    No Known Activations