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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "retired" and its variants, focusing on retirement transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    retirement and being retired

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     twe
    -0.44
     sense
    -0.41
     micros
    -0.38
     tween
    -0.37
     trench
    -0.37
     pad
    -0.37
     chica
    -0.36
     Sense
    -0.35
     Prom
    -0.35
     pre
    -0.35
    POSITIVE LOGITS
     retiring
    0.90
    retirement
    0.83
     retired
    0.83
     retires
    0.80
     retirement
    0.80
    retired
    0.79
    Cyfarwyddwr
    0.75
     retire
    0.74
     retirees
    0.70
     Retirement
    0.69
    Act Density 0.002%

    No Known Activations