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

    Neuronpedia

    INDEX
    Explanations

    pairings of prepositions and nouns related to territorial boundaries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical borders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶĢâĶĢâĶĢâĶĢ
    -0.70
    thora
    -0.69
    interest
    -0.68
    ]+
    -0.68
    oran
    -0.67
    oxide
    -0.66
    --+
    -0.66
    tle
    -0.66
    TD
    -0.65
    YL
    -0.65
    POSITIVE LOGITS
     borders
    1.14
     Borders
    0.91
     crossings
    0.83
     border
    0.80
    agos
    0.78
     boundaries
    0.75
     encl
    0.74
     gates
    0.70
     guarding
    0.67
    banks
    0.67
    Act Density 0.008%

    No Known Activations