INDEX
    Explanations

    references to time or temporal measurements

    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.16
    dehy
    -0.16
    bert
    -0.15
    ẩu
    -0.15
     overnight
    -0.15
    kus
    -0.15
    ertia
    -0.15
    emen
    -0.14
     last
    -0.14
    arez
    -0.14
    POSITIVE LOGITS
     time
    0.28
    from
    0.25
     nữa
    0.23
    .from
    0.21
     from
    0.21
    time
    0.21
    From
    0.20
    -time
    0.20
     From
    0.20
    -from
    0.19
    Act Density 0.022%

    No Known Activations