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

    Neuronpedia

    INDEX
    Explanations

    references to specific neighborhoods or areas

    oai_token-act-pair · gpt-3.5-turbo

    references to neighborhoods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inen
    -1.06
    indal
    -0.92
    xon
    -0.89
    uchin
    -0.80
    ulum
    -0.77
    cean
    -0.75
    emic
    -0.75
    andum
    -0.74
    gow
    -0.74
    vic
    -0.74
    POSITIVE LOGITS
     neighborhood
    0.96
     neighborhoods
    0.96
     neighbourhood
    0.96
     Neighborhood
    0.90
     neighbourhoods
    0.87
     streets
    0.85
     grocer
    0.83
     Borough
    0.82
     apartment
    0.79
     Neigh
    0.78
    Act Density 0.020%

    No Known Activations