INDEX
    Explanations

    references to a specific author or researcher

    New Auto-Interp
    Negative Logits
    +#+#
    -0.84
     MonoBehaviour
    -0.82
    nestjs
    -0.77
     ModelExpression
    -0.71
    UrlResolution
    -0.70
     PyObject
    -0.69
     TextInputType
    -0.68
    protoimpl
    -0.65
     BoxFit
    -0.63
    tagHelperRunner
    -0.63
    POSITIVE LOGITS
    isu
    1.63
     Bert
    1.55
    isy
    1.52
    Bert
    1.35
    usal
    0.95
     Bing
    0.71
    ISY
    0.60
     bert
    0.60
    Bing
    0.50
    endy
    0.50
    Act Density 0.001%

    No Known Activations