INDEX
    Explanations

    instances of the substring "Sk" across various contexts, indicating a focus on a specific entity or brand

    New Auto-Interp
    Negative Logits
    eÅŁ
    -0.16
    brahim
    -0.16
    iÅŁim
    -0.16
    eurs
    -0.15
    chio
    -0.15
    eo
    -0.15
    otomy
    -0.15
    aÅŁ
    -0.15
    esine
    -0.15
    hausen
    -0.14
    POSITIVE LOGITS
    illed
    0.31
    incare
    0.29
    ipped
    0.27
    ewed
    0.27
    ippy
    0.26
    etched
    0.25
    illet
    0.25
    inned
    0.25
    agit
    0.25
    okie
    0.25
    Act Density 0.022%

    No Known Activations