INDEX
    Explanations

    instances of personal pronouns and indirect references to people

    New Auto-Interp
    Negative Logits
    forth
    -0.16
    elf
    -0.15
    erc
    -0.14
    .layouts
    -0.14
    ikon
    -0.14
     è¾
    -0.14
    ousse
    -0.14
    ault
    -0.14
    окон
    -0.14
    odes
    -0.13
    POSITIVE LOGITS
    zych
    0.17
    å͝
    0.16
    edo
    0.15
    ADOW
    0.15
    adow
    0.15
    à¥įà¤Ĺ
    0.14
    alet
    0.14
    uiten
    0.14
     mainland
    0.14
    alom
    0.14
    Act Density 0.151%

    No Known Activations