INDEX
    Explanations

    This neuron detects occurrences of the word “shipping.”

    New Auto-Interp
    Negative Logits
     maze
    -0.07
    ์ล
    -0.06
    _note
    -0.06
     decorated
    -0.06
    otence
    -0.06
     resemble
    -0.06
     MySqlCommand
    -0.06
    _wheel
    -0.06
     avoidance
    -0.06
     consequat
    -0.06
    POSITIVE LOGITS
     shipped
    0.11
     shipping
    0.11
     Shipping
    0.10
    Shipping
    0.09
     shipments
    0.08
     postage
    0.08
    Ship
    0.08
     Ship
    0.08
    0.07
     chr
    0.07
    Act Density 0.006%

    No Known Activations