INDEX
    Explanations

    product reviews

    The neuron fires on e-commerce category labels (e.g. “Beauty & Personal Care,” “Office Products,” “Cookers & Ovens,” “Clothing, Shoes & Jewelry,” etc.).

    New Auto-Interp
    Negative Logits
    .toJson
    -0.06
     Citizenship
    -0.06
    rust
    -0.06
    \Response
    -0.06
    (fp
    -0.06
     شاه
    -0.06
     เอ
    -0.06
     NX
    -0.06
    وست
    -0.06
    一個
    -0.06
    POSITIVE LOGITS
    vx
    0.06
    0.06
     Garten
    0.06
     $↵↵
    0.06
    $value
    0.06
    .They
    0.06
    processable
    0.06
    mouseout
    0.06
    แท
    0.06
    .tight
    0.06
    Act Density 0.019%

    No Known Activations