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

    Neuronpedia

    INDEX
    Explanations

    locations and spatial relationships between them

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proximity or location, particularly related to streets and directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivities
    -0.76
    ebus
    -0.75
    aki
    -0.73
    orian
    -0.69
    rogram
    -0.68
    ronic
    -0.67
    imony
    -0.67
    seed
    -0.67
    uffle
    -0.66
    omic
    -0.65
    POSITIVE LOGITS
     entrances
    0.82
     downtown
    0.79
     corner
    0.77
     adjacent
    0.77
     entrance
    0.77
    tyard
    0.76
     overlook
    0.76
     vicinity
    0.75
    rium
    0.75
     campus
    0.75
    Act Density 0.221%

    No Known Activations