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

    Neuronpedia

    INDEX
    Explanations

    stories or anecdotes recounted by people

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences or stories shared by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     remains
    -0.70
    eded
    -0.65
    igned
    -0.62
     fuels
    -0.61
     exits
    -0.60
     swiftly
    -0.60
     pathways
    -0.60
     2024
    -0.59
    ede
    -0.59
     dictates
    -0.58
    POSITIVE LOGITS
     cowork
    0.83
     overheard
    0.74
    inav
    0.74
     acquaintance
    0.71
     interviewing
    0.68
     Professor
    0.67
     Minion
    0.66
    owder
    0.66
     newsp
    0.66
    infeld
    0.65
    Act Density 0.714%

    No Known Activations