INDEX
    Explanations

    mentions of notable individuals and their achievements

    New Auto-Interp
    Negative Logits
    оÑĢе
    -0.16
    ursal
    -0.16
    uspend
    -0.16
     поба
    -0.15
     otherwise
    -0.15
    ãģ¾ãģ¾
    -0.15
     meisten
    -0.15
     hopeful
    -0.14
    ofire
    -0.14
     sonst
    -0.14
    POSITIVE LOGITS
     die
    0.22
     das
    0.18
     eine
    0.18
    die
    0.15
    uppy
    0.15
     ÑģледÑĥÑİÑīие
    0.15
    heck
    0.15
     ihre
    0.14
    	die
    0.14
     dying
    0.14
    Act Density 0.039%

    No Known Activations