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

    Neuronpedia

    INDEX
    Explanations

    terms related to political discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to political issues or crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.74
    oji
    -0.68
    Pokemon
    -0.64
     haha
    -0.60
    Poké
    -0.57
    girlfriend
    -0.57
     mats
    -0.57
    Studio
    -0.57
    Fans
    -0.57
    Laughs
    -0.56
    POSITIVE LOGITS
     neocons
    0.88
    erity
    0.79
     repud
    0.78
     Kissinger
    0.78
     principled
    0.76
     socialists
    0.73
     Socialist
    0.72
    kefeller
    0.72
     Bolshe
    0.71
     moreover
    0.71
    Act Density 2.414%

    No Known Activations