INDEX
    Explanations

    links or buttons to share content on social media platforms

    phrases indicating interactions with digital content and social media elements

    New Auto-Interp
    Negative Logits
     ',
    -0.84
     metic
    -0.83
    !".
    -0.80
    .",
    -0.78
    !",
    -0.76
     ",
    -0.73
     traged
    -0.70
    ©¶æ
    -0.69
     '.
    -0.67
     reconc
    -0.67
    POSITIVE LOGITS
    )
    1.99
    )...
    1.43
    )(
    1.38
    )'
    1.36
    )"
    1.33
    ),
    1.33
    )—
    1.33
    )*
    1.29
    )+
    1.27
    )=
    1.26
    Act Density 0.108%

    No Known Activations