INDEX
    Explanations

    terms associated with empathy and sympathy

    New Auto-Interp
    Negative Logits
    ebi
    -0.17
    kl
    -0.16
     ý
    -0.16
    acci
    -0.15
    imore
    -0.15
    аниÑĨ
    -0.15
    egers
    -0.14
    als
    -0.14
    ÃŃt
    -0.14
    ller
    -0.14
    POSITIVE LOGITS
     sympath
    0.31
     sympathetic
    0.30
     sympathy
    0.29
     empath
    0.26
    compass
    0.26
     empathy
    0.25
     Sy
    0.23
    etic
    0.23
     towards
    0.23
     symp
    0.22
    Act Density 0.013%

    No Known Activations