INDEX
    Explanations

    references to emotional states and feelings related to the heart

    New Auto-Interp
    Negative Logits
    illas
    -0.16
    еж
    -0.16
    unas
    -0.15
    estar
    -0.15
    yon
    -0.15
    abad
    -0.15
    zej
    -0.14
     Spit
    -0.14
    cla
    -0.14
    REAM
    -0.14
    POSITIVE LOGITS
     hearts
    0.23
     Hearts
    0.23
    -heart
    0.22
    Heart
    0.20
     heart
    0.20
     Heart
    0.19
    heart
    0.18
    osemite
    0.16
    wand
    0.16
    å¿ĥ
    0.15
    Act Density 0.037%

    No Known Activations