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

    Neuronpedia

    INDEX
    Explanations

    political entities or figures of national or international significance

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries and their leaders or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govtrack
    -0.86
     glim
    -0.84
     ancest
    -0.71
    pite
    -0.70
    Downloadha
    -0.69
    idth
    -0.66
     Seym
    -0.66
    emale
    -0.65
    ulk
    -0.65
     ingred
    -0.64
    POSITIVE LOGITS
    20439
    0.72
     Rubin
    0.70
    bugs
    0.65
     missionaries
    0.65
    inch
    0.65
    AAF
    0.64
    oen
    0.61
    IRC
    0.60
    ileaks
    0.60
    jen
    0.59
    Act Density 0.516%

    No Known Activations