INDEX
    Explanations

    instances of the word "some" in various contexts

    New Auto-Interp
    Negative Logits
    wk
    -0.15
    aal
    -0.15
     æ¢
    -0.15
    sst
    -0.14
    umont
    -0.14
    overrides
    -0.14
     punt
    -0.14
    unkt
    -0.13
     Hermes
    -0.13
    arks
    -0.13
    POSITIVE LOGITS
    ething
    0.17
    (thing
    0.16
     Clare
    0.16
    ellido
    0.15
    place
    0.15
    许
    0.15
    ITHER
    0.14
    -times
    0.14
    ither
    0.14
    ras
    0.14
    Act Density 0.067%

    No Known Activations