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

    Neuronpedia

    INDEX
    Explanations

    relations between countries or regions and military activities or technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to military presence and logistical details in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >>\
    -0.79
    justice
    -0.76
    conom
    -0.75
    Politics
    -0.74
    annis
    -0.72
    agonist
    -0.72
    Goal
    -0.71
    aign
    -0.70
    account
    -0.70
    Luck
    -0.68
    POSITIVE LOGITS
     these
    1.15
     ones
    1.12
     tubes
    1.00
     bogus
    0.98
     them
    0.97
     machines
    0.94
     stickers
    0.92
     defective
    0.91
     pairs
    0.90
     boxes
    0.90
    Act Density 0.548%

    No Known Activations