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

    Neuronpedia

    INDEX
    Explanations

    the phrase "day to day"

    oai_token-act-pair · gpt-3.5-turbo

    references to daily life experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Osw
    -0.84
    arts
    -0.76
     Starts
    -0.69
    OTUS
    -0.68
    POST
    -0.67
    jon
    -0.66
    went
    -0.66
    art
    -0.65
     THEN
    -0.64
    iov
    -0.64
    POSITIVE LOGITS
     metab
    0.73
     variability
    0.71
     accessibility
    0.68
    ascript
    0.66
     visitation
    0.65
     interactions
    0.65
    etheless
    0.64
     fulfil
    0.62
    uracy
    0.61
     advis
    0.61
    Act Density 0.059%

    No Known Activations