INDEX
    Explanations

    enthusiasm and positive expressions about food and social events

    New Auto-Interp
    Negative Logits
    olla
    -0.16
    appy
    -0.16
    ожд
    -0.16
    avirus
    -0.15
    opian
    -0.15
    readcr
    -0.14
    ç£
    -0.14
    ungle
    -0.14
     Couldn
    -0.14
    ëĮĢíĸī
    -0.14
    POSITIVE LOGITS
     Bookmark
    0.18
    Bookmark
    0.18
     Pin
    0.16
     pin
    0.16
     seal
    0.15
     bookmark
    0.15
     Hub
    0.15
    Hub
    0.14
     Savings
    0.14
     Looks
    0.14
    Act Density 0.012%

    No Known Activations