INDEX
    Explanations

    instances of the word "except" in various contexts

    New Auto-Interp
    Negative Logits
    coni
    -0.19
    bak
    -0.15
    izza
    -0.15
    pone
    -0.15
    uments
    -0.14
    еÑĢÑĪ
    -0.14
    ço
    -0.14
    ither
    -0.14
    itzer
    -0.14
    lets
    -0.14
    POSITIVE LOGITS
    ing
    0.34
    ting
    0.22
    s
    0.20
    ING
    0.19
    ed
    0.19
    antly
    0.18
    een
    0.17
    wards
    0.17
    ive
    0.16
    ively
    0.16
    Act Density 0.011%

    No Known Activations