INDEX
    Explanations

    the phrase "for" consistently throughout the document

    New Auto-Interp
    Negative Logits
     Tub
    -0.15
    opic
    -0.15
    icao
    -0.15
    ieur
    -0.15
    ogr
    -0.14
    áme
    -0.14
    rr
    -0.14
    ATCH
    -0.13
     ETA
    -0.13
     tub
    -0.13
    POSITIVE LOGITS
    eson
    0.20
    Stamp
    0.15
    msp
    0.15
    onth
    0.15
    //{{
    0.15
    ADDE
    0.15
    canf
    0.15
    orny
    0.14
    estroy
    0.14
     temporary
    0.14
    Act Density 0.019%

    No Known Activations