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

    Neuronpedia

    INDEX
    Explanations

    references to killing and murder within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Farah
    -0.76
    Applicant
    -0.75
     vache
    -0.72
     متحده
    -0.71
     Manly
    -0.70
     Weeks
    -0.69
     grotte
    -0.69
    cerne
    -0.68
     ngl
    -0.67
    cheme
    -0.66
    POSITIVE LOGITS
     kill
    1.45
     kills
    1.41
     KILL
    1.38
     Kill
    1.36
    kill
    1.29
     killing
    1.28
     killed
    1.26
     Kills
    1.21
    kills
    1.20
     killings
    1.20
    Act Density 0.065%

    No Known Activations