INDEX
    Explanations

    occurrences of the phrase "of" in various contexts

    New Auto-Interp
    Negative Logits
    ANDOM
    -0.16
    ongo
    -0.15
    ajar
    -0.14
    born
    -0.14
    anzi
    -0.14
    nÃŃ
    -0.13
    anos
    -0.13
    consistent
    -0.13
    ile
    -0.13
     unlikely
    -0.13
    POSITIVE LOGITS
     times
    0.14
    archy
    0.14
    ick
    0.14
    aret
    0.14
     people
    0.14
    asty
    0.14
    ertz
    0.13
    ساÙĦ
    0.13
    303
    0.13
    çŃ
    0.13
    Act Density 0.064%

    No Known Activations