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

    Neuronpedia

    INDEX
    Explanations

    mentions of violent acts and criminal incidents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violent incidents and deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cola
    -0.95
    anium
    -0.76
    Weather
    -0.72
    adeon
    -0.71
    utical
    -0.70
    hern
    -0.68
    ignty
    -0.68
    hem
    -0.64
    glomer
    -0.64
    BuyableInstoreAndOnline
    -0.63
    POSITIVE LOGITS
     spree
    1.14
    âĶĢâĶĢ
    0.81
     rampage
    0.79
     sparked
    0.74
     unfold
    0.74
     perpetrated
    0.72
     ordeal
    0.67
     occurred
    0.66
     HMS
    0.66
     killings
    0.64
    Act Density 0.178%

    No Known Activations