INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Things
    -1.19
     houſe
    -1.07
     myſelf
    -1.06
     Houſe
    -1.05
     raiſ
    -1.02
    Things
    -1.00
     Jefus
    -1.00
     itſelf
    -1.00
     Theſe
    -0.99
     Monfieur
    -0.99
    POSITIVE LOGITS
     one
    0.80
     $
    0.77
    0.76
    ,
    0.67
     two
    0.65
     five
    0.64
     a
    0.60
     four
    0.59
     #
    0.57
    0.57
    Act Density 0.101%

    No Known Activations