INDEX
    Explanations

    references to organizations and foundations involved in social causes

    New Auto-Interp
    Negative Logits
    aç
    -0.15
    amble
    -0.14
    å£
    -0.14
    etting
    -0.14
    otle
    -0.14
    tura
    -0.14
     cl
    -0.14
    colo
    -0.14
    opping
    -0.14
    rov
    -0.14
    POSITIVE LOGITS
     tane
    0.15
    ãĥijãĥ³
    0.14
     CASCADE
    0.14
    weed
    0.14
    orget
    0.14
    annis
    0.14
    -CN
    0.14
    -org
    0.13
     Erotische
    0.13
    ction
    0.13
    Act Density 0.064%

    No Known Activations