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

    Neuronpedia

    INDEX
    Explanations

    mentions of military activities or plans

    oai_token-act-pair · gpt-3.5-turbo

    references to military actions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.86
    terness
    -0.81
    apest
    -0.81
    Honest
    -0.80
    âĶģ
    -0.77
    ï¸
    -0.76
     Michaels
    -0.76
    nob
    -0.76
    heimer
    -0.74
    Filename
    -0.73
    POSITIVE LOGITS
     fatig
    1.03
     commanders
    0.98
     dictatorship
    0.98
     personnel
    0.94
     readiness
    0.93
     acad
    0.92
     stationed
    0.90
     intervention
    0.90
     commander
    0.89
     intelligence
    0.89
    Act Density 0.024%

    No Known Activations