INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    _div
    -0.09
    Div
    -0.08
     Div
    -0.08
     congr
    -0.08
     criminal
    -0.08
     dies
    -0.08
     hul
    -0.08
     divert
    -0.08
     lined
    -0.08
    die
    -0.08
    POSITIVE LOGITS
    /graphql
    0.13
     queries
    0.10
     graphql
    0.10
     gql
    0.10
    graphql
    0.10
    查询
    0.10
    .graph
    0.10
    _queries
    0.10
    queries
    0.09
    -query
    0.09
    Act Density 0.002%

    No Known Activations