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

    Neuronpedia

    INDEX
    Explanations

    references to wars and military engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rette
    -0.17
     Farage
    -0.14
     Fukushima
    -0.14
    ilon
    -0.14
     Rebellion
    -0.14
     Thatcher
    -0.13
    ä¹ĺ
    -0.13
     recip
    -0.13
    imator
    -0.13
    abe
    -0.13
    POSITIVE LOGITS
     Afghanistan
    0.23
     Authorization
    0.21
    ghan
    0.21
     war
    0.21
     wars
    0.20
     troop
    0.20
     Iraq
    0.20
     military
    0.19
     mission
    0.19
     War
    0.19
    Act Density 0.089%

    No Known Activations