INDEX
    Explanations

    The neuron activates on occurrences of the word “cocaine.”

    New Auto-Interp
    Negative Logits
    _sp
    -0.07
    _bus
    -0.06
     decltype
    -0.06
     راهنم
    -0.06
    unda
    -0.06
    lesh
    -0.06
     temple
    -0.06
     الش
    -0.06
     grp
    -0.06
     Sund
    -0.06
    POSITIVE LOGITS
     cocaine
    0.13
    coc
    0.10
     recorded
    0.08
    (ic
    0.07
     Coca
    0.07
     Classical
    0.07
     Opening
    0.07
     oxy
    0.07
     recording
    0.07
     carnival
    0.07
    Act Density 0.002%

    No Known Activations