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

    Neuronpedia

    INDEX
    Explanations

    mentions of violent acts, particularly bombings

    oai_token-act-pair · gpt-3.5-turbo

    references to bombing incidents or campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.93
    videos
    -0.75
    ITY
    -0.72
    learn
    -0.72
    MpServer
    -0.71
    galitarian
    -0.70
    dit
    -0.70
    los
    -0.69
    FINE
    -0.69
    olars
    -0.69
    POSITIVE LOGITS
     bombing
    1.16
     bombings
    0.99
     bomber
    0.96
     raids
    0.95
     spree
    0.89
     barr
    0.89
     bombers
    0.88
     bombard
    0.87
     shelter
    0.83
     shelters
    0.83
    Act Density 0.024%

    No Known Activations