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

    Neuronpedia

    INDEX
    Explanations

    computer code elements and terms

    oai_token-act-pair · gpt-3.5-turbo

    references to social issues or societal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anniversary
    -0.64
     Books
    -0.64
    ournals
    -0.62
    ormons
    -0.62
    iversary
    -0.61
    ospels
    -0.61
    icipated
    -0.60
     Tomorrow
    -0.59
    ennial
    -0.58
    ottest
    -0.58
    POSITIVE LOGITS
     inability
    0.67
     contagious
    0.63
     mistrust
    0.63
     lack
    0.61
     causation
    0.59
     perce
    0.59
     misplaced
    0.58
    effic
    0.57
     flares
    0.57
    efficiency
    0.57
    Act Density 1.696%

    No Known Activations