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

    Neuronpedia

    INDEX
    Explanations

    terms related to pensions and retirement funds

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

    pension related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wright
    -0.51
    Wright
    -0.49
    United
    -0.43
     SWAT
    -0.41
    Wat
    -0.41
    DW
    -0.40
     Fillmore
    -0.40
    var
    -0.39
    ADAM
    -0.39
     United
    -0.39
    POSITIVE LOGITS
     pension
    2.16
     Pension
    2.14
    Pension
    1.97
     pensions
    1.80
    pension
    1.71
     Pensions
    1.63
     pensioners
    1.41
    ENSION
    0.95
    annuation
    0.87
    养老
    0.83
    Act Density 0.003%

    No Known Activations