INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ſelf
    -1.26
     itſelf
    -1.23
     purpoſe
    -1.18
     Efq
    -1.17
     myſelf
    -1.14
    ſelves
    -1.13
     raiſ
    -1.13
     Anſ
    -1.10
     pleaſure
    -1.03
     ―――――
    -1.01
    POSITIVE LOGITS
    s
    0.50
    in
    0.47
    an
    0.47
     i
    0.46
     (
    0.46
    ,
    0.46
    ery
    0.45
     en
    0.45
     In
    0.44
    .
    0.44
    Act Density 0.114%

    No Known Activations