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

    Neuronpedia

    INDEX
    Explanations

    locations and places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    status
    -0.81
    Privacy
    -0.77
    inance
    -0.75
    vana
    -0.73
    ":""},{"
    -0.71
    mbudsman
    -0.68
    undo
    -0.67
    neutral
    -0.65
    DIV
    -0.65
    isman
    -0.65
    POSITIVE LOGITS
     Avenue
    0.90
     Nights
    0.82
     Yard
    0.77
     Lights
    0.77
     Ave
    0.77
     Mayhem
    0.76
     Rite
    0.75
     Fried
    0.75
     Comic
    0.74
     Skies
    0.73
    Act Density 0.326%

    No Known Activations