INDEX
    Explanations

    instances of the word "but" used to contrast or introduce an exception

    New Auto-Interp
    Negative Logits
    κÏĮ
    -0.16
    ã썿ĢĿãģĨ
    -0.15
    ãĥªãĥ¼ãĤº
    -0.14
    indir
    -0.14
    erce
    -0.14
    ounty
    -0.14
    ylum
    -0.14
    /DD
    -0.14
    incare
    -0.14
    ipzig
    -0.14
    POSITIVE LOGITS
     then
    0.24
     maybe
    0.23
    then
    0.23
    Then
    0.20
    _then
    0.20
    Maybe
    0.19
     Then
    0.19
    THEN
    0.19
     Maybe
    0.19
     THEN
    0.19
    Act Density 0.107%

    No Known Activations