Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𬭤
    -0.07
     obsess
    -0.07
    谁知
    -0.06
    Calendar
    -0.06
     Henry
    -0.06
    礞
    -0.06
    zp
    -0.06
    ě
    -0.06
     прогноз
    -0.06
     Chan
    -0.06
    POSITIVE LOGITS
    	system
    0.08
     ddl
    0.07
    _EXPRESSION
    0.07
     Cabinets
    0.07
     아래
    0.07
    .responseText
    0.07
     Calls
    0.07
     critically
    0.06
     typeid
    0.06
    ควร
    0.06
    Act Density 0.004%

    No Known Activations