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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the president and references to elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Local
    -0.61
     Dise
    -0.61
     Monsters
    -0.60
     Puzzles
    -0.60
     Mortal
    -0.60
    TOR
    -0.60
    âĵĺ
    -0.59
     Mechanics
    -0.58
    Unity
    -0.58
    Kings
    -0.57
    POSITIVE LOGITS
    ially
    1.09
    ial
    0.98
     himself
    0.94
    clinton
    0.89
    manship
    0.83
    's
    0.80
    alty
    0.79
    berries
    0.79
    elect
    0.78
    aroo
    0.77
    Act Density 0.067%

    No Known Activations