INDEX
    Explanations

    mentions of the location "Santa Monica."

    mentions of "Santa" and related terms

    New Auto-Interp
    Negative Logits
    edly
    -0.81
    irection
    -0.70
    ochond
    -0.70
    staking
    -0.68
    intent
    -0.66
    ives
    -0.64
    lessly
    -0.64
    buffer
    -0.64
    epad
    -0.63
    eenth
    -0.62
    POSITIVE LOGITS
     Claus
    1.54
     Clara
    1.08
     Monica
    0.99
     Ana
    0.96
     Barbara
    0.93
     Rosa
    0.90
     Clar
    0.88
     Maria
    0.87
     Clause
    0.87
     Cruz
    0.86
    Act Density 0.010%

    No Known Activations