INDEX
    Explanations

    classmates and teammates

    New Auto-Interp
    Negative Logits
     mentors
    0.62
     mentor
    0.61
     adherents
    0.57
     ally
    0.56
     spouse
    0.54
     partner
    0.54
     followers
    0.52
     mentorship
    0.51
     affiliate
    0.50
     disciple
    0.50
    POSITIVE LOGITS
     classmates
    1.44
     classmate
    1.30
    同学
    1.16
    同學
    1.05
    同學們
    1.02
    同学们
    0.95
     teammates
    0.89
     fellow
    0.83
     teammate
    0.75
     compañeros
    0.71
    Act Density 0.016%

    No Known Activations