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

    Neuronpedia

    INDEX
    Explanations

    mentions of governments and countries

    oai_token-act-pair · gpt-3.5-turbo

    references to specific governments and nations involved in geopolitical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     1886
    -0.68
    inas
    -0.63
    outine
    -0.63
    archy
    -0.62
    scoring
    -0.62
     Chatt
    -0.61
     Title
    -0.61
     basics
    -0.60
     Shall
    -0.60
     Vert
    -0.59
    POSITIVE LOGITS
     Embassy
    0.90
     embassy
    0.84
     diplomats
    0.83
    AAF
    0.81
     diplomat
    0.76
     Diplom
    0.75
     airstrikes
    0.73
     diplomatic
    0.73
    ITED
    0.72
     intervene
    0.72
    Act Density 0.439%

    No Known Activations