INDEX
    Explanations

    instances of comments or interactions related to the text

    New Auto-Interp
    Negative Logits
     Peer
    -0.16
    eki
    -0.16
     Cooke
    -0.15
    asar
    -0.14
    ingle
    -0.14
    iyi
    -0.14
    alsy
    -0.14
     Gomez
    -0.13
    706
    -0.13
     TFT
    -0.13
    POSITIVE LOGITS
    unga
    0.19
    regnum
    0.17
    burg
    0.15
    urg
    0.15
    baum
    0.14
    .Stretch
    0.14
    orent
    0.14
    ãĥ¼ãĥł
    0.14
    upp
    0.13
    zon
    0.13
    Act Density 0.008%

    No Known Activations