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

    Neuronpedia

    INDEX
    Explanations

    information related to military activities and international conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to military capabilities and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiIcon
    -0.83
    malink
    -0.72
    ãĤ¬
    -0.69
    rition
    -0.68
    APTER
    -0.67
     presumption
    -0.66
    iquette
    -0.64
    itivity
    -0.63
    Reviewer
    -0.62
     Facts
    -0.62
    POSITIVE LOGITS
     ultraviolet
    0.82
     roadside
    0.68
    yond
    0.68
    expensive
    0.68
     mundane
    0.66
     downright
    0.65
     ranging
    0.64
     trucks
    0.64
    lying
    0.64
     hundreds
    0.63
    Act Density 0.493%

    No Known Activations