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

    Neuronpedia

    INDEX
    Explanations

    religious buildings or terms related to politics and international relations

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to technology, societal issues, and controversial topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SAP
    -0.60
     Scientific
    -0.58
     Flavoring
    -0.56
    hap
    -0.55
    atom
    -0.55
     Tropical
    -0.55
    Mp
    -0.54
    local
    -0.54
    Audio
    -0.54
     Western
    -0.53
    POSITIVE LOGITS
     sucks
    0.78
     rul
    0.69
     sucked
    0.68
     whis
    0.65
     etiquette
    0.64
     pudding
    0.63
    Champ
    0.62
    gate
    0.62
     ain
    0.61
    $$$$
    0.61
    Act Density 0.923%

    No Known Activations