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

    Neuronpedia

    INDEX
    Explanations

    locations, particularly those based on cardinal directions like eastern and western

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical directions and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sharp
    -1.02
    oku
    -0.91
    Deal
    -0.87
    BALL
    -0.86
    Pool
    -0.84
    Pos
    -0.83
    Applic
    -0.82
    Poll
    -0.80
    Filter
    -0.79
    Jump
    -0.78
    POSITIVE LOGITS
     hemisphere
    1.05
    most
    0.94
     regions
    0.89
     periphery
    0.88
     suburbs
    0.83
     border
    0.82
     provinces
    0.80
    querque
    0.80
     districts
    0.79
     region
    0.79
    Act Density 0.025%

    No Known Activations