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

    Neuronpedia

    INDEX
    Explanations

    references to geographical borders

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical borders and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    visors
    -0.67
    ibur
    -0.66
    ctive
    -0.64
    DER
    -0.64
    obe
    -0.64
     partName
    -0.64
    orah
    -0.64
    odder
    -0.63
    ynasty
    -0.63
    otos
    -0.62
    POSITIVE LOGITS
     borders
    1.05
     Borders
    0.92
     border
    0.82
    lines
    0.79
    ansas
    0.78
     crossings
    0.76
    rants
    0.74
    layer
    0.73
    border
    0.72
    radius
    0.71
    Act Density 0.013%

    No Known Activations