INDEX
    Explanations

    becomes clear or obvious

    New Auto-Interp
    Negative Logits
     asfalto
    -0.89
    cruiser
    -0.84
    fitrión
    -0.81
    crypto
    -0.80
    burgers
    -0.79
    peka
    -0.78
     movimenta
    -0.77
    uuuu
    -0.77
    Pancake
    -0.75
     saisons
    -0.75
    POSITIVE LOGITS
     clear
    4.16
     evident
    3.53
     obvious
    3.34
     apparent
    3.30
    clear
    3.03
    evident
    2.67
     оче
    2.44
    Clear
    2.41
     evidente
    2.33
     Clear
    2.27
    Act Density 0.041%

    No Known Activations