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

    Neuronpedia

    INDEX
    Explanations

    mentions of high-profile individuals in a political or public service context

    oai_token-act-pair · gpt-3.5-turbo

    references to former officials or public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acht
    -0.75
    anche
    -0.71
    TPS
    -0.71
    antics
    -0.70
    achus
    -0.68
    atics
    -0.67
     brace
    -0.67
    ñ
    -0.66
    urga
    -0.66
    plings
    -0.65
    POSITIVE LOGITS
    Former
    0.98
     Former
    0.96
    ly
    0.90
    Veter
    0.76
    bies
    0.71
     former
    0.69
    theless
    0.68
    ity
    0.66
     Vice
    0.65
    nesses
    0.65
    Act Density 0.012%

    No Known Activations