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

    Neuronpedia

    INDEX
    Explanations

    proper names of cities

    oai_token-act-pair · gpt-3.5-turbo

    references to the city or organization associated with San Francisco

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tons
    -0.66
    raints
    -0.65
    itiz
    -0.64
    kson
    -0.63
    opter
    -0.62
    selves
    -0.62
    erous
    -0.60
    letes
    -0.60
    geist
    -0.60
    atively
    -0.59
    POSITIVE LOGITS
    MAN
    1.42
    VILLE
    1.41
    LAND
    1.36
    BUR
    1.33
    INGTON
    1.33
    ANA
    1.32
    COL
    1.32
    STON
    1.31
    STER
    1.31
    ENN
    1.31
    Act Density 0.076%

    No Known Activations