INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     coworker
    0.88
    Friend
    0.86
     Friend
    0.83
    friend
    0.82
     buddy
    0.72
    相手
    0.70
     anger
    0.68
     flirting
    0.68
     friendship
    0.67
     colleague
    0.67
    POSITIVE LOGITS
     families
    4.48
     family
    4.20
    Families
    4.07
     Families
    4.06
    families
    3.89
    Family
    3.84
    family
    3.83
     Family
    3.81
     famílias
    3.76
     família
    3.73
    Act Density 0.165%

    No Known Activations