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 activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dit
    -0.81
    galitarian
    -0.80
    gling
    -0.75
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.74
    Sync
    -0.69
    zl
    -0.65
    VO
    -0.65
    ðĿ
    -0.63
    flex
    -0.63
    ixed
    -0.63
    POSITIVE LOGITS
    abad
    1.03
     spree
    0.93
     terrorism
    0.87
    ophobic
    0.86
     perpetrated
    0.86
     mastermind
    0.85
     bombings
    0.84
    ISM
    0.80
     Terrorism
    0.79
    ophobia
    0.79
    Act Density 0.031%

    No Known Activations