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

    Neuronpedia

    INDEX
    Explanations

    words related to inciting anger or conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or events that incite conflict or tension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Accounting
    -0.88
    ummer
    -0.74
    haul
    -0.72
    aum
    -0.72
    rake
    -0.70
    amacare
    -0.70
    ultz
    -0.66
    ewater
    -0.66
    oard
    -0.66
    fficiency
    -0.65
    POSITIVE LOGITS
     provocation
    1.16
     provoke
    1.02
     provoking
    0.97
     bystanders
    0.88
     provocative
    0.88
     provoked
    0.83
     prov
    0.81
     aggression
    0.79
     sidx
    0.79
     escalation
    0.79
    Act Density 0.033%

    No Known Activations