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

    Neuronpedia

    INDEX
    Explanations

    words related to urban settings or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to streets or street-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emort
    -0.90
    merce
    -0.88
    essee
    -0.81
    igham
    -0.80
    opsis
    -0.77
    ividual
    -0.73
    abase
    -0.72
    uania
    -0.72
    xit
    -0.72
    racuse
    -0.71
    POSITIVE LOGITS
    cars
    1.08
    lights
    0.99
    fighter
    0.89
    wear
    0.88
    ways
    0.86
    fare
    0.83
    light
    0.82
    car
    0.80
     corners
    0.80
    walk
    0.79
    Act Density 0.040%

    No Known Activations