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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iciary
    -0.95
    Fuck
    -0.83
    Coach
    -0.82
    swick
    -0.78
    ocracy
    -0.77
    Rated
    -0.77
    Deal
    -0.76
    biz
    -0.75
    ocrat
    -0.74
    obook
    -0.73
    POSITIVE LOGITS
     researchers
    1.46
     scientists
    1.38
     studies
    1.35
     methodological
    1.30
     observational
    1.26
     biologists
    1.23
     hypotheses
    1.20
     empirical
    1.18
     physicists
    1.12
     anecdotal
    1.12
    Act Density 0.331%

    No Known Activations