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

    Neuronpedia

    INDEX
    Explanations

    words related to attacks or warfare

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to attacks and military operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utical
    -0.88
    erential
    -0.83
    natureconservancy
    -0.74
    ollar
    -0.73
    é¾įå
    -0.70
    phia
    -0.70
    heit
    -0.70
     trustworthy
    -0.69
    ensical
    -0.69
    é¾įåĸļ士
    -0.68
    POSITIVE LOGITS
     gunfire
    0.71
     Killing
    0.68
     mob
    0.68
     Massacre
    0.68
     rampage
    0.66
    ÃĥÃĤ
    0.66
     bombings
    0.65
     perpetrated
    0.65
     injuring
    0.65
     helicopters
    0.64
    Act Density 0.675%

    No Known Activations