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

    Neuronpedia

    INDEX
    Explanations

    references to different countries, governmental activities, and political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to political entities, governments, and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utations
    -0.66
    gment
    -0.64
     opportunity
    -0.63
    eanor
    -0.62
    uality
    -0.59
    resy
    -0.59
    phies
    -0.58
     opportunities
    -0.58
     turnout
    -0.58
    tions
    -0.58
    POSITIVE LOGITS
     against
    0.73
    Interstitial
    0.70
    ateurs
    0.68
     itself
    0.67
     towards
    0.66
     during
    0.66
    Cart
    0.65
     onwards
    0.64
     themselves
    0.64
     himself
    0.64
    Act Density 0.542%

    No Known Activations