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

    Neuronpedia

    INDEX
    Explanations

    controversial topics or terms

    oai_token-act-pair · gpt-3.5-turbo

    the concept of controversy or contentious issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Eng
    -0.71
     sust
    -0.70
    LET
    -0.68
     Dealer
    -0.68
    pour
    -0.67
    craft
    -0.67
    cells
    -0.67
    tu
    -0.66
    Craft
    -0.65
    Write
    -0.64
    POSITIVE LOGITS
     controversial
    3.48
     contentious
    2.48
    roversial
    2.09
     divisive
    2.00
     controvers
    1.93
     unpopular
    1.82
     provocative
    1.79
     controversies
    1.64
     controversy
    1.63
     disputed
    1.62
    Act Density 0.025%

    No Known Activations