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

    Neuronpedia

    INDEX
    Explanations

    references to urban streets or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of streets or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igham
    -0.86
    emonic
    -0.83
    emort
    -0.81
    xit
    -0.79
    merce
    -0.78
     Archdemon
    -0.73
    uchin
    -0.72
    ividual
    -0.70
    attery
    -0.70
    gow
    -0.68
    POSITIVE LOGITS
    cars
    1.05
    lights
    0.91
    fare
    0.90
    fighter
    0.86
    walk
    0.85
    gap
    0.83
    wear
    0.81
     street
    0.81
    street
    0.79
    walker
    0.76
    Act Density 0.021%

    No Known Activations