INDEX
    Explanations

    punctuation marks, specifically the period

    New Auto-Interp
    Negative Logits
    harma
    -0.19
     tượng
    -0.15
    erosis
    -0.14
    .accel
    -0.14
    inos
    -0.14
    vented
    -0.14
    вед
    -0.14
    Dyn
    -0.14
     dyn
    -0.14
    igne
    -0.14
    POSITIVE LOGITS
    æ¡Ĥ
    0.15
     ment
    0.15
     cat
    0.14
    oyal
    0.14
    uously
    0.14
    ardown
    0.14
    wiki
    0.14
    -cat
    0.14
     Leaf
    0.13
    acia
    0.13
    Act Density 0.001%

    No Known Activations