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

    Neuronpedia

    INDEX
    Explanations

    keywords related to terrorism

    oai_token-act-pair · gpt-3.5-turbo

    references to terrorism and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    galitarian
    -0.85
    gling
    -0.81
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.77
    dit
    -0.75
    Sync
    -0.69
    çĦ
    -0.67
    ixed
    -0.66
     Fiat
    -0.65
    ðĿ
    -0.65
    gran
    -0.64
    POSITIVE LOGITS
    abad
    1.03
     terrorism
    0.98
     spree
    0.92
     Terrorism
    0.86
     perpetrated
    0.85
     bombings
    0.84
    ophobic
    0.84
     mastermind
    0.82
    ISM
    0.82
    ophobia
    0.80
    Act Density 0.021%

    No Known Activations