INDEX
    Explanations

    references to time, specifically the word "month"

    references to time periods, specifically the word "month" and its associated context

    New Auto-Interp
    Negative Logits
     needle
    -0.69
     textual
    -0.68
     sy
    -0.65
    UTF
    -0.65
    abilia
    -0.63
     scope
    -0.60
     Tray
    -0.59
     cores
    -0.59
    tap
    -0.58
    resource
    -0.58
    POSITIVE LOGITS
    ruary
    0.96
     afternoon
    0.84
    lished
    0.74
     evening
    0.74
    ı
    0.73
     semester
    0.71
     mornings
    0.71
    女
    0.71
    alez
    0.70
     Marino
    0.70
    Act Density 0.083%

    No Known Activations