INDEX
    Explanations

    This neuron activates on occurrences of the word “product.”

    New Auto-Interp
    Negative Logits
    clud
    -0.07
    ileged
    -0.07
    TA
    -0.07
    stacles
    -0.07
    tah
    -0.06
    usterity
    -0.06
     onViewCreated
    -0.06
     tone
    -0.06
    steps
    -0.06
    _fk
    -0.06
    POSITIVE LOGITS
     developing
    0.07
     Islamic
    0.07
     jel
    0.07
     abuse
    0.06
     här
    0.06
     jets
    0.06
     кафед
    0.06
     jen
    0.06
     annihil
    0.06
     COMPUTER
    0.06
    Act Density 0.040%

    No Known Activations