INDEX
    Explanations

    terms related to communication and social interaction

    New Auto-Interp
    Negative Logits
    alem
    -0.17
    ero
    -0.15
    ider
    -0.15
    @qq
    -0.14
    anel
    -0.14
    ît
    -0.14
    andel
    -0.14
    idla
    -0.13
    orp
    -0.13
     پش
    -0.13
    POSITIVE LOGITS
    obuf
    0.16
    -scalable
    0.14
    defgroup
    0.14
    ptal
    0.13
    ecer
    0.13
    adol
    0.13
    ÛĮÙħÛĮ
    0.13
    UBLE
    0.13
    ocha
    0.13
    eme
    0.13
    Act Density 0.011%

    No Known Activations