INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     emitter
    -0.07
    _left
    -0.07
     domains
    -0.07
    .sp
    -0.07
     liquid
    -0.06
    artz
    -0.06
     Borough
    -0.06
     stro
    -0.06
     object
    -0.06
    endors
    -0.06
    POSITIVE LOGITS
     vaccine
    0.11
     Vaccine
    0.10
     vaccinations
    0.08
     vaccines
    0.08
     vaccination
    0.07
    VIC
    0.07
     kabil
    0.06
     Vacc
    0.06
     Wine
    0.06
     insure
    0.06
    Act Density 0.008%

    No Known Activations