INDEX
    Explanations

    references to mental health issues, specifically depression

    New Auto-Interp
    Negative Logits
    eria
    -0.16
    abaj
    -0.15
    erty
    -0.14
    izzo
    -0.14
    enna
    -0.14
    bal
    -0.13
    gem
    -0.13
    les
    -0.13
    Ñįн
    -0.13
    ActionTypes
    -0.13
    POSITIVE LOGITS
    Ïĥκε
    0.15
    iteli
    0.14
    anka
    0.14
     ãĥĿ
    0.14
     libero
    0.14
     Chand
    0.14
    รà¸Ķ
    0.14
    ichick
    0.14
    ods
    0.13
    allet
    0.13
    Act Density 0.107%

    No Known Activations