INDEX
    Explanations

    mathematical symbols, particularly the symbol 'R' and related symbols

    New Auto-Interp
    Negative Logits
     Efq
    -1.07
     avoient
    -1.03
    >--}}
    -1.01
     ainfi
    -0.98
     ſtate
    -0.98
     laſt
    -0.96
     enfans
    -0.96
     uſe
    -0.95
     étoit
    -0.95
     purpoſe
    -0.95
    POSITIVE LOGITS
     D
    0.66
    0.66
    '
    0.60
    0.60
    ussis
    0.60
    ,
    0.59
     G
    0.59
    \
    0.58
     W
    0.58
      
    0.58
    Act Density 0.329%

    No Known Activations