INDEX
    Explanations

    discourse about climate change and activism

    New Auto-Interp
    Negative Logits
    éri
    -0.15
    earable
    -0.14
    bject
    -0.14
    FFF
    -0.14
    oultry
    -0.13
    abad
    -0.13
    bourg
    -0.13
    onu
    -0.13
    ologi
    -0.13
    _literals
    -0.13
    POSITIVE LOGITS
    vos
    0.16
    inden
    0.16
    470
    0.16
    oser
    0.15
     modest
    0.14
    (IB
    0.14
    _WRAP
    0.14
    dbuf
    0.13
    ÑĩаÑĤ
    0.13
     Painter
    0.13
    Act Density 0.032%

    No Known Activations