INDEX
    Explanations

    The neuron fires on words naming gaming hardware and performance metrics (e.g. console, consoles, Stadia, lag).

    New Auto-Interp
    Negative Logits
     Similar
    -0.07
    24
    -0.07
    -fast
    -0.06
    16
    -0.06
    Learning
    -0.06
     공개
    -0.06
    ë
    -0.06
    -0.06
    aec
    -0.06
    ubat
    -0.05
    POSITIVE LOGITS
     Newly
    0.07
     Ivanka
    0.07
     AIS
    0.07
    SEQUENTIAL
    0.06
     inauguration
    0.06
    _place
    0.06
     Cupertino
    0.06
     distra
    0.06
    Michelle
    0.06
    )(
    0.06
    Act Density 0.158%

    No Known Activations