INDEX
    Explanations

    phrases and words related to spatial contexts, particularly emphasizing external environments or entities associated with the term "outside."

    New Auto-Interp
    Negative Logits
    ž
    -0.16
    uby
    -0.15
    semb
    -0.15
    opo
    -0.15
    pron
    -0.14
    itto
    -0.14
    ;element
    -0.14
    cek
    -0.14
    975
    -0.13
    ruh
    -0.13
    POSITIVE LOGITS
    ndx
    0.17
    uelles
    0.16
    alars
    0.15
     Pleasant
    0.15
     Lev
    0.15
    walls
    0.15
     å£
    0.15
    âh
    0.14
     directly
    0.14
     strictly
    0.14
    Act Density 0.170%

    No Known Activations