INDEX
    Explanations

    vaccination and disease

    New Auto-Interp
    Negative Logits
     Infectious
    1.62
     virus
    1.60
     инфек
    1.59
    感染
    1.58
     infectious
    1.57
     vírus
    1.56
     infections
    1.54
     infection
    1.52
     Virus
    1.51
    Virus
    1.50
    POSITIVE LOGITS
     hand
    0.78
     aspirin
    0.74
     herd
    0.71
     long
    0.67
     Long
    0.67
     grads
    0.65
     dishwasher
    0.64
     monolith
    0.64
     gymnastics
    0.63
     internships
    0.62
    Act Density 0.029%

    No Known Activations