INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     infection
    -1.55
     infected
    -1.55
     Infection
    -1.53
    infection
    -1.46
     infect
    -1.46
    Infection
    -1.37
    infected
    -1.36
     Infected
    -1.33
     Infections
    -1.30
     infección
    -1.24
    POSITIVE LOGITS
     with
    0.73
    arity
    0.58
     by
    0.54
    ary
    0.47
    Portale
    0.47
    isNew
    0.47
    Geplaatst
    0.46
    stå
    0.46
    ']")
    0.45
    ality
    0.44
    Act Density 0.015%

    No Known Activations