INDEX
    Explanations

    punctuation or sentence-ending elements

    New Auto-Interp
    Negative Logits
    eyse
    -0.17
     Ash
    -0.15
     brig
    -0.15
    IVEN
    -0.15
    vious
    -0.15
     Dash
    -0.14
    strings
    -0.14
    enthal
    -0.14
     Reform
    -0.14
    ellig
    -0.14
    POSITIVE LOGITS
    °
    0.16
    idal
    0.16
    å²
    0.15
    ãĥ¼ãĥį
    0.14
    burgh
    0.14
    764
    0.14
    dag
    0.14
    aspers
    0.14
    ugi
    0.14
    .hex
    0.14
    Act Density 0.000%

    No Known Activations