INDEX
    Explanations

    prepositions and compound prepositional phrases

    New Auto-Interp
    Negative Logits
     latter
    -0.18
    $MESS
    -0.18
    deaux
    -0.17
    udeau
    -0.15
    $LANG
    -0.15
    .wordpress
    -0.14
    659
    -0.14
    lij
    -0.14
    /INFO
    -0.14
    ubb
    -0.14
    POSITIVE LOGITS
    gether
    0.28
    atre
    0.23
    clusive
    0.21
    ftware
    0.20
    -the
    0.19
    -one
    0.19
    apons
    0.17
    ir
    0.17
    oret
    0.17
    stride
    0.17
    Act Density 0.066%

    No Known Activations