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

    Neuronpedia

    INDEX
    Explanations

    terms related to causing harm or injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.82
    cius
    -0.79
    ortment
    -0.76
    runner
    -0.73
    shore
    -0.71
    mbuds
    -0.69
    zyme
    -0.68
    chrom
    -0.68
     Ou
    -0.68
    clinton
    -0.67
    POSITIVE LOGITS
     wounds
    1.10
     havoc
    1.06
     inflicted
    1.02
     damage
    0.99
     inflict
    0.97
     injuries
    0.87
     carnage
    0.86
     humiliation
    0.84
     inflic
    0.83
     griev
    0.83
    Act Density 0.013%

    No Known Activations