INDEX
    Explanations

    phrases indicating concern or consideration about a situation

    New Auto-Interp
    Negative Logits
    ulous
    -0.16
    339
    -0.15
     licens
    -0.15
    ling
    -0.15
     ling
    -0.14
    ůl
    -0.13
    ogan
    -0.13
    شتر
    -0.13
    337
    -0.13
    ä
    -0.13
    POSITIVE LOGITS
    iets
    0.16
    елен
    0.15
    gings
    0.15
    acker
    0.15
     cÃł
    0.15
    ampie
    0.15
    ackers
    0.14
    piler
    0.14
    CRY
    0.14
    akah
    0.14
    Act Density 0.074%

    No Known Activations