INDEX
    Explanations

    The neuron fires on occurrences of the stem “ischemi-,” i.e. words referring to ischemia or ischemic.

    New Auto-Interp
    Negative Logits
     deposits
    -0.07
    (T
    -0.07
     Walters
    -0.07
     Tat
    -0.06
     Bon
    -0.06
     Bart
    -0.06
     FU
    -0.06
     pets
    -0.06
     tal
    -0.06
     ro
    -0.06
    POSITIVE LOGITS
     ischem
    0.17
    іка
    0.07
    IRM
    0.07
     Shim
    0.07
    reeze
    0.07
     شرقی
    0.07
    сих
    0.07
     lstm
    0.07
     Isabel
    0.07
     Erica
    0.07
    Act Density 0.003%

    No Known Activations