INDEX
    Explanations

    terms related to societal structure and class systems

    New Auto-Interp
    Negative Logits
    zend
    -0.19
    azu
    -0.17
    rei
    -0.17
    zen
    -0.15
    aga
    -0.15
    qa
    -0.14
    oyo
    -0.14
    γκα
    -0.14
    cola
    -0.14
    zzo
    -0.14
    POSITIVE LOGITS
    oine
    0.15
    ICC
    0.14
    符
    0.14
    ÑĥÑĩ
    0.14
    oenix
    0.13
     सव
    0.13
    emouth
    0.13
    -hero
    0.13
     Found
    0.13
    oin
    0.13
    Act Density 0.184%

    No Known Activations