INDEX
    Explanations

    mentions of the concept of "the past."

    New Auto-Interp
    Negative Logits
    ered
    -0.18
    icut
    -0.18
    iÃŁ
    -0.16
    hart
    -0.16
    kel
    -0.16
    _PROPERTY
    -0.15
    otor
    -0.15
    åύ
    -0.15
    estar
    -0.14
    olid
    -0.14
    POSITIVE LOGITS
    /current
    0.23
    ures
    0.21
    ebin
    0.20
    ime
    0.19
    imes
    0.18
    iche
    0.18
    URES
    0.17
    omba
    0.17
    most
    0.17
     glory
    0.16
    Act Density 0.026%

    No Known Activations