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

    Neuronpedia

    INDEX
    Explanations

    words related to political terrorism

    oai_token-act-pair · gpt-3.5-turbo

    references to terrorism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    galitarian
    -0.82
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.81
    dit
    -0.78
    gling
    -0.72
    ðĿ
    -0.70
    ixed
    -0.69
    Sync
    -0.69
    VO
    -0.68
    ta
    -0.66
    çĦ
    -0.65
    POSITIVE LOGITS
    abad
    0.99
     spree
    0.96
     terrorism
    0.95
     perpetrated
    0.86
     bombings
    0.84
     mastermind
    0.82
    ophobic
    0.82
     bombing
    0.82
     terrorists
    0.82
    ISIS
    0.81
    Act Density 0.015%

    No Known Activations