INDEX
    Explanations

    the word "fix" or some variation of it

    New Auto-Interp
    Negative Logits
     Monfieur
    -1.53
     Shakspeare
    -1.28
     Jefus
    -1.27
    ſelves
    -1.20
    ſelf
    -1.19
     itſelf
    -1.19
     Reſ
    -1.17
     pleaſure
    -1.16
     faſt
    -1.14
     houſe
    -1.13
    POSITIVE LOGITS
    tagHelperRunner
    0.63
     Bus
    0.59
    jspb
    0.58
     authorisation
    0.57
    cic
    0.56
     I
    0.54
     A
    0.54
    ↵↵
    0.54
     realising
    0.53
    atelle
    0.53
    Act Density 2.251%

    No Known Activations