INDEX
    Explanations

    the word "About" in various contexts, indicating a focus on describing or introducing topics

    New Auto-Interp
    Negative Logits
    akis
    -0.15
    utes
    -0.14
    abra
    -0.14
    Ñģо
    -0.14
     indeed
    -0.14
    udiant
    -0.14
    iba
    -0.14
     Dil
    -0.14
    ented
    -0.14
    ught
    -0.14
    POSITIVE LOGITS
    FindBy
    0.15
    avr
    0.15
    á»ķ
    0.14
    Derived
    0.14
    977
    0.14
    oldown
    0.14
    ledged
    0.14
     Ðijол
    0.14
    olls
    0.14
    VERRIDE
    0.14
    Act Density 0.012%

    No Known Activations