INDEX
    Explanations

    punctuation marks, specifically periods

    New Auto-Interp
    Negative Logits
    opher
    -0.16
    hum
    -0.14
    rie
    -0.14
    blo
    -0.14
    cent
    -0.14
     Ribbon
    -0.14
     Montgomery
    -0.14
    andest
    -0.14
    552
    -0.13
    ces
    -0.13
    POSITIVE LOGITS
    SURE
    0.16
    .djangoproject
    0.15
    .bc
    0.15
    ocr
    0.14
    ojis
    0.14
    heimer
    0.14
    874
    0.14
    acers
    0.14
    oj
    0.14
    oland
    0.14
    Act Density 0.002%

    No Known Activations