INDEX
    Explanations

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

    New Auto-Interp
    Negative Logits
     plush
    -0.07
     evenings
    -0.07
     onAnimation
    -0.07
    _even
    -0.07
    _numpy
    -0.06
    Ever
    -0.06
    ACS
    -0.06
    Responsive
    -0.06
    structors
    -0.06
     usually
    -0.06
    POSITIVE LOGITS
    τικό
    0.06
     рев
    0.06
     αυτό
    0.06
     LIN
    0.06
    	names
    0.06
    하며
    0.06
    061
    0.06
     lassen
    0.06
    flags
    0.06
    KER
    0.06
    Act Density 0.047%

    No Known Activations