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

    Neuronpedia

    INDEX
    Explanations

    countries or geopolitical entities

    oai_token-act-pair · gpt-3.5-turbo

    references to political entities and nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eanor
    -0.65
    chwitz
    -0.65
    risome
    -0.63
    comings
    -0.62
     havoc
    -0.61
     resil
    -0.60
    anwhile
    -0.60
    valued
    -0.60
    iqueness
    -0.59
    atche
    -0.59
    POSITIVE LOGITS
     contractor
    0.70
     architects
    0.65
    erity
    0.61
     manufacturer
    0.60
    icians
    0.59
     contractors
    0.59
     Writers
    0.59
     consortium
    0.59
    º
    0.58
    ateurs
    0.58
    Act Density 0.742%

    No Known Activations