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

    Neuronpedia

    INDEX
    Explanations

    mentions of positions of authority or seniority

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "senior" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pel
    -0.95
    closed
    -0.80
    doors
    -0.78
    tails
    -0.77
    bones
    -0.73
    weet
    -0.70
    bags
    -0.70
    door
    -0.70
    apesh
    -0.67
    last
    -0.67
    POSITIVE LOGITS
    ity
    1.22
     citizen
    0.98
     citiz
    0.93
     lecturer
    0.90
     advisor
    0.87
     citizens
    0.86
     adviser
    0.84
     thesis
    0.79
    ities
    0.77
     fellow
    0.76
    Act Density 0.032%

    No Known Activations