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

    Neuronpedia

    INDEX
    Explanations

    references to significant historical wars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lionel
    -0.17
     èĤ
    -0.15
    -License
    -0.15
    à¹Ģà¸ģล
    -0.14
    untu
    -0.13
    wich
    -0.13
    /do
    -0.13
    _OM
    -0.13
    (HWND
    -0.13
    eliness
    -0.12
    POSITIVE LOGITS
     War
    0.62
     war
    0.54
    War
    0.46
    -war
    0.43
    war
    0.43
     WAR
    0.42
    _war
    0.40
     Wars
    0.35
     Ware
    0.35
    warf
    0.34
    Act Density 0.029%

    No Known Activations