INDEX
    Explanations

    common/commons

    The neuron activates on occurrences of the word “common” or “commons,” marking references to shared or communal resources.

    New Auto-Interp
    Negative Logits
     Shaft
    -0.08
    rightarrow
    -0.07
    etre
    -0.07
     responseType
    -0.07
     врач
    -0.06
    Step
    -0.06
     Israeli
    -0.06
     reputed
    -0.06
    Entre
    -0.06
     stro
    -0.06
    POSITIVE LOGITS
     Commons
    0.08
    \Common
    0.08
     कम
    0.07
    .Common
    0.07
    /common
    0.07
    commons
    0.07
     unicorn
    0.07
     कन
    0.07
    _COMM
    0.07
    .common
    0.07
    Act Density 0.012%

    No Known Activations