INDEX
    Explanations

    temporal references and time-related phrases

    New Auto-Interp
    Negative Logits
     Gir
    -0.15
    enger
    -0.15
    ERIC
    -0.15
    iras
    -0.15
     todd
    -0.15
    hoe
    -0.15
    sein
    -0.14
    olet
    -0.14
    umont
    -0.14
    umper
    -0.14
    POSITIVE LOGITS
    lid
    0.15
    enville
    0.15
    ollen
    0.14
    ufs
    0.14
     lid
    0.14
    ehr
    0.14
    mand
    0.14
    rust
    0.14
    uffed
    0.14
     mand
    0.14
    Act Density 0.135%

    No Known Activations