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

    Neuronpedia

    INDEX
    Explanations

    mentions of urban environments

    oai_token-act-pair · gpt-3.5-turbo

    references to urban areas and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.95
    cius
    -0.91
    yip
    -0.89
    hemy
    -0.83
    othal
    -0.82
    etsk
    -0.82
    uth
    -0.79
    uden
    -0.79
    terday
    -0.78
    bley
    -0.77
    POSITIVE LOGITS
    ization
    0.99
    scape
    0.97
    ized
    0.91
     dwell
    0.89
    icity
    0.85
    izing
    0.82
     renewal
    0.78
     explorers
    0.77
     guerrilla
    0.77
    isation
    0.77
    Act Density 0.015%

    No Known Activations