INDEX
    Explanations

    mentions of the name "Paul" in various contexts

    New Auto-Interp
    Negative Logits
    essor
    -0.16
    activex
    -0.16
    εί
    -0.15
    reta
    -0.15
    ακ
    -0.15
    emmel
    -0.15
    orse
    -0.14
    metatable
    -0.14
    nist
    -0.14
    emd
    -0.14
    POSITIVE LOGITS
    son
    0.27
    ine
    0.27
    sen
    0.24
    raj
    0.23
    sson
    0.20
    ie
    0.20
    sons
    0.19
    ien
    0.18
    s
    0.18
    ina
    0.18
    Act Density 0.023%

    No Known Activations