INDEX
    Explanations

    neuronal activity, development, surgery, communication

    New Auto-Interp
    Negative Logits
    i
    1.23
    as
    1.21
    en
    1.17
    um
    1.15
    ur
    1.13
    it
    1.09
    l
    1.09
    at
    1.02
    na
    1.00
    un
    0.96
    POSITIVE LOGITS
    тся
    0.98
     neurons
    0.98
    )">
    0.89
    ;
    0.84
    ,
    0.78
     neuron
    0.77
    )(
    0.76
    ).
    0.76
    ,*/}
    0.73
    ος
    0.73
    Act Density 0.016%

    No Known Activations