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

    Neuronpedia

    INDEX
    Explanations

    large numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unct
    -0.71
    inav
    -0.70
    imedia
    -0.67
    claimer
    -0.64
    abus
    -0.62
    Reviewer
    -0.61
    aban
    -0.61
    agents
    -0.61
    arist
    -0.61
    lass
    -0.60
    POSITIVE LOGITS
     consecutive
    0.95
     percent
    0.91
     additional
    0.85
     fewer
    0.79
    %
    0.78
     apiece
    0.76
     minutes
    0.75
     total
    0.75
     million
    0.75
     Deg
    0.73
    Act Density 0.321%

    No Known Activations