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

    Neuronpedia

    INDEX
    Explanations

    instances of violence or casualties reported in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹Īà¸Ńà¸ĩ
    -0.17
    ":[{↵
    -0.15
    ipay
    -0.14
     зап
    -0.14
    __$
    -0.13
    ÑĸÑĤÑĥ
    -0.13
     Survivor
    -0.13
    èĬ¯
    -0.13
    ç¯
    -0.13
    ãĤ«ãĥ¼
    -0.13
    POSITIVE LOGITS
     died
    0.50
     dies
    0.41
     killed
    0.40
     die
    0.38
     death
    0.37
     dying
    0.35
     deaths
    0.35
     dead
    0.34
     Killed
    0.34
     Died
    0.32
    Act Density 0.284%

    No Known Activations