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

    Neuronpedia

    INDEX
    Explanations

    terms related to political borders

    oai_token-act-pair · gpt-3.5-turbo

    references to territorial boundaries or borders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thora
    -0.82
    oran
    -0.74
    é¾įå
    -0.68
    DAY
    -0.67
    --+
    -0.67
    ]+
    -0.67
    odo
    -0.67
    TYPE
    -0.66
    interest
    -0.65
    umption
    -0.65
    POSITIVE LOGITS
     borders
    1.34
     Borders
    0.93
     border
    0.90
     crossings
    0.82
     boundaries
    0.81
    border
    0.78
     censor
    0.76
     Border
    0.76
     bordering
    0.75
    agos
    0.73
    Act Density 0.005%

    No Known Activations