INDEX
    Explanations

    always certain descriptive words

    New Auto-Interp
    Negative Logits
     iconic
    0.53
     generational
    0.47
     foundational
    0.44
     Focal
    0.43
     surm
    0.42
     cicat
    0.42
     hearsay
    0.42
     focal
    0.41
     fearless
    0.41
     generics
    0.41
    POSITIVE LOGITS
     сумма
    0.52
    loge
    0.44
    layer
    0.43
    動力
    0.43
    lish
    0.43
    MESH
    0.42
    等於
    0.41
    unjungi
    0.41
    ilikom
    0.41
    公路
    0.40
    Act Density 0.000%

    No Known Activations