INDEX
    Explanations

    phrases related to expressing feelings and emotions

    New Auto-Interp
    Negative Logits
    attern
    -0.15
    abant
    -0.15
    cour
    -0.14
    dbuf
    -0.14
    stead
    -0.14
     Spicer
    -0.14
    ataires
    -0.14
    ãĥ¼ãĤ¹
    -0.14
    ivar
    -0.14
    frey
    -0.14
    POSITIVE LOGITS
    IDO
    0.18
    одÑĥ
    0.16
    наÑĩе
    0.16
    гл
    0.15
    aise
    0.15
    <small
    0.15
    ogan
    0.15
    VEST
    0.15
    importe
    0.14
    umb
    0.14
    Act Density 0.048%

    No Known Activations