INDEX
    Explanations

    names and references related to prominent individuals

    New Auto-Interp
    Negative Logits
    timeofday
    -0.17
    yme
    -0.16
    _framework
    -0.16
    nee
    -0.16
    lia
    -0.16
    aram
    -0.15
    ernals
    -0.15
    ylon
    -0.14
    ikes
    -0.14
    ldkf
    -0.14
    POSITIVE LOGITS
    oster
    0.18
    аза
    0.16
     Carpenter
    0.16
    vig
    0.14
    åģ
    0.14
     countryside
    0.14
     Lor
    0.14
    ed
    0.14
    ruta
    0.13
    çĮ«
    0.13
    Act Density 0.025%

    No Known Activations