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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations or points of interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     delinqu
    -0.77
    ESE
    -0.76
    HS
    -0.71
     chemically
    -0.70
     metabol
    -0.70
    thy
    -0.70
    ccording
    -0.69
    natureconservancy
    -0.69
    uthor
    -0.68
    XY
    -0.68
    POSITIVE LOGITS
     Point
    1.13
    point
    1.10
    Point
    0.98
    patrick
    0.90
    points
    0.81
     Forward
    0.81
    pad
    0.78
    hole
    0.78
     Bree
    0.78
    Points
    0.77
    Act Density 0.012%

    No Known Activations