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

    Neuronpedia

    INDEX
    Explanations

    terms related to killing and homicide

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Farah
    -0.74
    setRequest
    -0.66
    Applicant
    -0.65
     متحده
    -0.65
     Himo
    -0.65
     Weise
    -0.63
    umumkan
    -0.63
     Folks
    -0.62
    Brus
    -0.62
     Weeks
    -0.61
    POSITIVE LOGITS
     kill
    1.62
     kills
    1.57
     KILL
    1.57
     Kill
    1.49
     killing
    1.49
     killed
    1.46
    kill
    1.42
     Kills
    1.35
     Killed
    1.34
     killings
    1.34
    Act Density 0.093%

    No Known Activations