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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to terrorism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to terrorism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    galitarian
    -0.87
    )=(
    -0.81
    ðĿ
    -0.80
    laus
    -0.76
    aver
    -0.76
    shire
    -0.76
    pel
    -0.73
    elf
    -0.73
    rose
    -0.71
    dit
    -0.70
    POSITIVE LOGITS
     mastermind
    1.06
     terrorist
    0.99
    abad
    0.99
     bombings
    0.99
     bombing
    0.96
     terrorists
    0.91
     bombers
    0.91
     attacks
    0.89
     terrorism
    0.86
     spree
    0.84
    Act Density 0.021%

    No Known Activations