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

    Neuronpedia

    INDEX
    Explanations

    statistics and survey results

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating statistical data or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.88
    ollah
    -0.69
    sort
    -0.69
    alph
    -0.67
    capt
    -0.64
    edin
    -0.64
    dict
    -0.64
    idel
    -0.63
    archive
    -0.63
    card
    -0.62
    POSITIVE LOGITS
     respondents
    1.02
     households
    0.82
     surveyed
    0.80
     GDP
    0.76
    pees
    0.76
     polled
    0.75
     overall
    0.71
     variance
    0.70
     Fortune
    0.69
     Americans
    0.69
    Act Density 0.072%

    No Known Activations