INDEX
    Explanations

    phrases related to the concept of "for" or the purpose of something

    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.65
    AndEndTag
    -0.59
    }{*}{}
    -0.55
     виправивши
    -0.54
     Ather
    -0.54
    unhofer
    -0.54
    Ezek
    -0.54
    ństw
    -0.52
     Ganze
    -0.52
    DockStyle
    -0.52
    POSITIVE LOGITS
    RegressionTest
    0.73
    écial
    0.68
     for
    0.62
     для
    0.60
     fürs
    0.59
     ДЛЯ
    0.59
    для
    0.59
    用于
    0.58
    برای
    0.57
     spécial
    0.57
    Act Density 0.300%

    No Known Activations