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

    Neuronpedia

    INDEX
    Explanations

    references to ownership or people who own something

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities as "owners."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Airl
    -0.96
    ilde
    -0.77
    psey
    -0.76
    eday
    -0.75
    schild
    -0.75
    inx
    -0.71
    bil
    -0.68
     MacArthur
    -0.68
     Burst
    -0.67
    ilitary
    -0.67
    POSITIVE LOGITS
     owner
    0.82
    owners
    0.80
     beware
    0.78
     owners
    0.76
    owner
    0.75
     occup
    0.74
    pers
    0.72
    nings
    0.71
    parents
    0.71
     LIC
    0.71
    Act Density 0.022%

    No Known Activations