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

    Neuronpedia

    INDEX
    Explanations

    instances of legal or official matters and events

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ontent
    -0.74
    ratulations
    -0.73
    scape
    -0.67
    heit
    -0.66
    erva
    -0.65
    LOG
    -0.64
    atherine
    -0.64
    gans
    -0.63
    ional
    -0.62
    thia
    -0.62
    POSITIVE LOGITS
     outset
    1.39
     behest
    1.31
     forefront
    1.13
     same
    1.08
     expense
    1.08
     helm
    1.05
     end
    0.97
     moment
    0.97
     intersections
    0.96
     highest
    0.94
    Act Density 0.159%

    No Known Activations