INDEX
    Explanations

    personal pronouns and expressions of individual perspective

    New Auto-Interp
    Negative Logits
     незавершена
    -0.90
    rouvez
    -0.84
     uſed
    -0.84
    ^(@)
    -0.83
     pleaſure
    -0.82
     itſelf
    -0.81
    脚注の使い方
    -0.81
     juſ
    -0.80
     ThemeData
    -0.80
     myſelf
    -0.80
    POSITIVE LOGITS
    x
    0.58
    blog
    0.54
    <eos>
    0.50
     x
    0.50
     blog
    0.48
     I
    0.48
    ...
    0.48
     tumblr
    0.47
    0.46
    f
    0.46
    Act Density 0.065%

    No Known Activations