INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     noDo
    -0.37
     متعلقه
    -0.30
     BEEN
    -0.30
     armées
    -0.29
    gangen
    -0.29
     кото
    -0.28
     בעל
    -0.28
    gatron
    -0.28
     THEY
    -0.27
    tablissements
    -0.27
    POSITIVE LOGITS
     spring
    1.63
     Spring
    1.39
    Spring
    1.38
    spring
    1.30
     springtime
    1.29
     SPRING
    1.22
    SPRING
    1.19
     printemps
    1.13
     primavera
    1.13
     Frühjahr
    1.00
    Act Density 0.007%

    No Known Activations