INDEX
    Explanations

    references to rock climbing activities and notable climbs

    New Auto-Interp
    Negative Logits
    tra
    -0.16
    vig
    -0.15
    TRA
    -0.15
    Ùijت
    -0.15
    гов
    -0.14
    izzling
    -0.14
    çĽ
    -0.14
    Ordinal
    -0.14
    Ñĸв
    -0.14
    iye
    -0.14
    POSITIVE LOGITS
    childs
    0.17
    elen
    0.15
    hee
    0.15
    MBER
    0.15
     spoiler
    0.14
     faces
    0.14
    aren
    0.13
     bande
    0.13
    acy
    0.13
     spoil
    0.13
    Act Density 0.047%

    No Known Activations