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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals who have retired

    oai_token-act-pair · gpt-3.5-turbo

    mentions of retirement, specifically the term "retired" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grimm
    -0.76
    ellen
    -0.75
    antics
    -0.70
    arta
    -0.70
    ñ
    -0.70
    gs
    -0.68
    NG
    -0.67
    aug
    -0.66
    bring
    -0.66
    owitz
    -0.66
    POSITIVE LOGITS
     retiring
    0.95
     retired
    0.88
     retire
    0.80
    Veter
    0.76
     soldier
    0.75
     retirement
    0.73
    ired
    0.73
    dinand
    0.71
     retirees
    0.71
     colonel
    0.71
    Act Density 0.010%

    No Known Activations