INDEX
    Explanations

    Health problems

    This neuron responds to mentions of extreme body‐weight figures and their associated severe health or mobility consequences.

    New Auto-Interp
    Negative Logits
    -0.07
     Teach
    -0.07
    Size
    -0.07
    anken
    -0.06
    -0.06
     sad
    -0.06
    ivid
    -0.06
    EQUAL
    -0.06
     gains
    -0.06
     vượt
    -0.06
    POSITIVE LOGITS
     eleg
    0.07
     Р
    0.06
    0.06
     unreliable
    0.06
     daddy
    0.06
     '"+
    0.06
     pří
    0.06
     renamed
    0.06
     Burma
    0.06
    guards
    0.05
    Act Density 0.006%

    No Known Activations