INDEX
    Explanations

    skirts and clothes

    The neuron fires on mentions of sexually provocative or revealing clothing descriptions.

    New Auto-Interp
    Negative Logits
     breweries
    -0.07
     productions
    -0.07
     dicts
    -0.06
    ById
    -0.06
     tests
    -0.06
    [ip
    -0.06
     predictions
    -0.06
     eat
    -0.06
     negative
    -0.06
     liquids
    -0.06
    POSITIVE LOGITS
    ามารถ
    0.07
    рав
    0.07
    isayar
    0.07
    メント
    0.07
     destabil
    0.07
    اريخ
    0.07
    での
    0.06
     endPoint
    0.06
    	atomic
    0.06
    .PREFERRED
    0.06
    Act Density 0.022%

    No Known Activations