INDEX
    Explanations

    the words related to children's experiences or health

    New Auto-Interp
    Negative Logits
    ↵↵
    -0.53
    ↵↵↵↵
    -0.47
    handle
    -0.44
    isti
    -0.44
    .
    -0.42
     tarihi
    -0.41
    @
    -0.41
    ↵↵↵
    -0.41
    ento
    -0.40
    ma
    -0.40
    POSITIVE LOGITS
    Personendaten
    1.33
    awtextra
    1.24
     صوتيه
    1.19
    InjectAttribute
    1.14
    <bos>
    1.14
    SequentialGroup
    1.10
     resourceCulture
    1.10
    IsContent
    1.09
    AccessorTable
    1.08
     AssemblyCulture
    1.06
    Act Density 0.634%

    No Known Activations