INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Theſe
    -1.05
     Anſ
    -0.86
    ^(@)
    -0.84
    |}{$
    -0.84
     Monfieur
    -0.81
     Jefus
    -0.77
     myſelf
    -0.75
     ་་
    -0.74
    bibinfo
    -0.73
     Majefty
    -0.73
    POSITIVE LOGITS
     a
    0.64
    GEBURTSDATUM
    0.62
     in
    0.60
     so
    0.60
    0.53
    ValueStyle
    0.51
    ,
    0.49
    誰か
    0.49
     and
    0.48
     it
    0.47
    Act Density 0.047%

    No Known Activations