INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ordinates
    -0.08
     sc
    -0.07
     задач
    -0.07
    priet
    -0.07
     Yelp
    -0.07
     fj
    -0.07
    -0.07
    -0.07
    (Task
    -0.07
    -0.07
    POSITIVE LOGITS
     vaccinations
    0.17
     vaccination
    0.14
     vaccines
    0.14
    0.14
     prophyl
    0.13
    Vacc
    0.13
     vacinação
    0.13
     steril
    0.12
     вакцина
    0.12
     vacun
    0.12
    Act Density 0.014%

    No Known Activations