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

    Neuronpedia

    INDEX
    Explanations

    words related to terrorist activities and attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to terrorist acts and attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dit
    -0.85
    galitarian
    -0.75
    cius
    -0.73
     Canal
    -0.73
    natureconservancy
    -0.69
    DIT
    -0.69
    DOC
    -0.66
     Parables
    -0.66
     ropes
    -0.65
    é¾įå
    -0.65
    POSITIVE LOGITS
     bombing
    1.12
     spree
    1.09
     perpetrated
    1.04
     bombings
    1.02
     rampage
    0.88
     bombers
    0.86
     bomber
    0.86
     terror
    0.83
     terrorism
    0.83
    abad
    0.81
    Act Density 0.079%

    No Known Activations