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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical actions and military activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emoc
    -0.15
    upert
    -0.15
    arga
    -0.15
    ruk
    -0.14
    phin
    -0.14
    leh
    -0.14
    Ymd
    -0.14
    SError
    -0.13
    lev
    -0.13
    UTO
    -0.13
    POSITIVE LOGITS
     exercises
    0.25
     drills
    0.25
     provoc
    0.23
     provocative
    0.23
     Exercises
    0.22
     Exercise
    0.22
     exercise
    0.22
     exercised
    0.20
     sim
    0.20
     militar
    0.19
    Act Density 0.064%

    No Known Activations