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

    Neuronpedia

    INDEX
    Explanations

    mentions of military actions or strategies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of military activities or forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸
    -0.84
    ļéĨĴ
    -0.83
     Literary
    -0.83
    âĶģ
    -0.82
    Honest
    -0.80
    terness
    -0.77
    nob
    -0.76
     Michaels
    -0.75
    Msg
    -0.75
    Filename
    -0.74
    POSITIVE LOGITS
     dictatorship
    1.03
     commanders
    1.01
     intervention
    0.99
     fatig
    0.94
     readiness
    0.94
     coup
    0.93
     commander
    0.92
     involvement
    0.91
     modernization
    0.91
     deployment
    0.89
    Act Density 0.046%

    No Known Activations