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

    Neuronpedia

    INDEX
    Explanations

    references to positions of authority, particularly the role of president

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

    President and title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ins
    -0.37
     Ins
    -0.30
    httphttps
    -0.30
    aw
    -0.29
     مرئيه
    -0.29
    vin
    -0.29
     stre
    -0.29
     Ment
    -0.29
     MENT
    -0.28
     grond
    -0.27
    POSITIVE LOGITS
     president
    0.70
    President
    0.69
    Presidents
    0.68
     faſt
    0.67
     President
    0.66
     Monfieur
    0.65
    WriteBarrier
    0.65
     presidents
    0.64
    ſelf
    0.63
    CloseOperation
    0.63
    Act Density 0.006%

    No Known Activations