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

    Neuronpedia

    INDEX
    Explanations

    mentions of events or social gatherings involving dinner

    oai_token-act-pair · gpt-3.5-turbo

    references to dinner events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DEP
    -0.70
    shr
    -0.69
     Weld
    -0.66
    ulative
    -0.66
    negative
    -0.63
    Engineers
    -0.63
    abilities
    -0.63
    articles
    -0.63
     Agency
    -0.63
    STEM
    -0.63
    POSITIVE LOGITS
     dinner
    1.44
     dinners
    1.42
     meal
    1.25
     meals
    1.22
     supper
    1.21
     Dinner
    1.10
     lunch
    1.02
     banquet
    0.97
    halla
    0.96
     breakfast
    0.94
    Act Density 0.012%

    No Known Activations