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

    Neuronpedia

    INDEX
    Explanations

    specific locations within a city, specifically "City Hall"

    oai_token-act-pair · gpt-3.5-turbo

    references to government buildings and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onal
    -0.79
    rieg
    -0.79
    onom
    -0.68
    METHOD
    -0.65
    cause
    -0.64
    omi
    -0.64
    ubi
    -0.63
    wage
    -0.63
    м
    -0.63
    adapt
    -0.62
    POSITIVE LOGITS
     Correspond
    0.94
     Plaza
    0.86
     Buildings
    0.86
     Observatory
    0.85
     entrance
    0.83
     Building
    0.83
    assies
    0.81
     Headquarters
    0.80
     plaza
    0.80
     courtyard
    0.79
    Act Density 0.099%

    No Known Activations