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

    Neuronpedia

    INDEX
    Explanations

    references to cities and urban areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themſelves
    -0.89
    complexContent
    -0.86
    BeginInit
    -0.81
     Infin
    -0.81
     mariée
    -0.81
     Rumania
    -0.78
     Saxons
    -0.78
     Suprema
    -0.77
     cuánt
    -0.76
     myſelf
    -0.75
    POSITIVE LOGITS
     City
    2.23
     city
    2.14
     CITY
    2.02
    City
    1.89
     cities
    1.81
    city
    1.79
    CITY
    1.75
     Cities
    1.65
    cities
    1.58
    Cities
    1.57
    Act Density 0.034%

    No Known Activations