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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and border crossings

    oai_token-act-pair · gpt-3.5-turbo

    geographical or border-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STEM
    -0.82
    orians
    -0.76
    chool
    -0.75
     CEOs
    -0.71
     tenants
    -0.70
     architects
    -0.69
     roomm
    -0.69
    owment
    -0.67
     condos
    -0.66
     Architects
    -0.66
    POSITIVE LOGITS
     porous
    1.17
     border
    1.15
    border
    1.14
     Strait
    1.11
     borders
    1.08
     Euph
    1.07
     rivers
    0.98
     waterways
    0.97
     disputed
    0.97
     airspace
    0.96
    Act Density 0.243%

    No Known Activations