INDEX
    Explanations

    words related to numbers or counting

    New Auto-Interp
    Negative Logits
    illin
    -0.62
    ussion
    -0.61
    ãĥīãĥ©
    -0.61
    ãĥŁ
    -0.61
    Buyable
    -0.61
    oga
    -0.60
    Roaming
    -0.60
    Dispatch
    -0.58
    BuyableInstoreAndOnline
    -0.57
    Fla
    -0.56
    POSITIVE LOGITS
     NEVER
    0.76
     huh
    0.75
     itself
    0.75
     EVERY
    0.75
     THEN
    0.74
    whatever
    0.71
     ONLY
    0.71
    etheless
    0.70
     everywhere
    0.70
     ALSO
    0.70
    Act Density 0.814%

    No Known Activations