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

    Neuronpedia

    INDEX
    Explanations

    topics or instances related to controversies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urances
    -0.75
    onz
    -0.66
    lasses
    -0.66
    ingers
    -0.65
    avement
    -0.64
    urance
    -0.63
    endar
    -0.63
     intest
    -0.62
    doors
    -0.62
    ells
    -0.62
    POSITIVE LOGITS
     controversy
    0.94
    naire
    0.90
     controversies
    0.89
     revolving
    0.85
     uproar
    0.84
     flared
    0.81
     involving
    0.81
     erupted
    0.80
     raged
    0.78
     arises
    0.78
    Act Density 0.019%

    No Known Activations