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

    Neuronpedia

    INDEX
    Explanations

    entities related to official bodies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental and organizational entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.86
    abiding
    -0.70
    acca
    -0.70
    addafi
    -0.69
    ocrates
    -0.69
    oldemort
    -0.69
    arettes
    -0.69
    DonaldTrump
    -0.68
     Guests
    -0.67
     hereafter
    -0.66
    POSITIVE LOGITS
     watchdog
    1.12
     Bureau
    1.02
     spokesman
    1.00
     spokesperson
    0.98
     Investigative
    0.98
     spokeswoman
    0.94
     Department
    0.94
     secretary
    0.94
     inspector
    0.93
     coroner
    0.93
    Act Density 0.346%

    No Known Activations