INDEX
    Explanations

    words indicating size, weight, or capacity

    New Auto-Interp
    Negative Logits
    ively
    -0.16
     Pett
    -0.16
    ortal
    -0.15
     subt
    -0.14
    ibernate
    -0.14
    ibur
    -0.14
    373
    -0.13
    idual
    -0.13
    oha
    -0.13
    gom
    -0.13
    POSITIVE LOGITS
     enough
    0.36
     Enough
    0.24
    Enough
    0.22
     nhất
    0.21
     hơn
    0.21
    EST
    0.19
    est
    0.19
    niejs
    0.18
    thest
    0.18
    essler
    0.18
    Act Density 0.226%

    No Known Activations