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

    Neuronpedia

    INDEX
    Explanations

    positions or roles in different organizations or jobs held by individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to job roles and positions within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -0.75
     yourselves
    -0.71
    nice
    -0.67
    gger
    -0.64
     ourselves
    -0.62
    Ey
    -0.60
    Fin
    -0.60
    anium
    -0.59
     Cors
    -0.59
     Koreans
    -0.59
    POSITIVE LOGITS
    mate
    0.89
    mates
    0.88
    abilities
    0.80
     overseeing
    0.77
    span
    0.76
     colleague
    0.75
     duties
    0.75
    uty
    0.71
    ername
    0.70
     responsibilities
    0.70
    Act Density 0.136%

    No Known Activations