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

    Neuronpedia

    INDEX
    Explanations

    terms related to murder and suicide

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     كومونز
    -0.61
    cento
    -0.58
    titutions
    -0.56
    ficit
    -0.52
    })));
    -0.51
    ModelSerializer
    -0.50
    الحياه
    -0.50
    锈钢
    -0.50
     EconPapers
    -0.50
    hezza
    -0.49
    POSITIVE LOGITS
     death
    1.10
    death
    0.97
     killing
    0.94
     suicide
    0.91
     deaths
    0.90
     murdering
    0.83
    Death
    0.82
     DEATH
    0.82
     kill
    0.81
    suicide
    0.80
    Act Density 0.452%

    No Known Activations