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

    Neuronpedia

    INDEX
    Explanations

    mentions of authority figures, particularly presidents

    oai_token-act-pair · gpt-3.5-turbo

    references to the president and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.70
     Mortal
    -0.64
     Mechdragon
    -0.63
     Casting
    -0.63
     Monsters
    -0.62
     Albion
    -0.61
     Dise
    -0.61
    Brave
    -0.61
     Tales
    -0.61
    TOR
    -0.61
    POSITIVE LOGITS
    ially
    1.11
    clinton
    0.94
    ial
    0.92
    manship
    0.87
     himself
    0.87
    trump
    0.84
     Barack
    0.80
    berries
    0.80
     appoint
    0.79
     pard
    0.79
    Act Density 0.051%

    No Known Activations