INDEX
    Explanations

    time-related phrases and durations

    New Auto-Interp
    Negative Logits
     sı
    -0.15
     Roz
    -0.15
    agr
    -0.14
    _TestCase
    -0.14
    983
    -0.14
     brief
    -0.14
    gue
    -0.14
     HIM
    -0.14
    usan
    -0.14
    enin
    -0.14
    POSITIVE LOGITS
     ká»ĥ
    0.23
     after
    0.21
     desde
    0.18
     counted
    0.18
     depuis
    0.18
    alendar
    0.18
     поÑģле
    0.17
     dopo
    0.17
    distance
    0.17
    _after
    0.17
    Act Density 0.080%

    No Known Activations