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

    Neuronpedia

    INDEX
    Explanations

    mentions of murder and unlawful killings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quette
    -0.16
     Thief
    -0.16
    æĪĴ
    -0.15
    anke
    -0.14
    ·æĸ°
    -0.14
     thieves
    -0.14
    ovna
    -0.14
    inium
    -0.14
    à¸Ĺาà¸Ļ
    -0.14
    üz
    -0.14
    POSITIVE LOGITS
     kill
    0.67
     killing
    0.67
     kills
    0.59
    kill
    0.58
     Kill
    0.56
     killed
    0.55
    Kill
    0.55
     killings
    0.55
     Killing
    0.54
    _kill
    0.53
    Act Density 0.369%

    No Known Activations