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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals, particularly political figures or religious leaders

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evangelical Christianity and associated figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ority
    -0.80
    Arthur
    -0.75
    izoph
    -0.75
    Else
    -0.75
    士
    -0.74
    Ķ
    -0.71
    neapolis
    -0.71
    rance
    -0.71
    teness
    -0.68
    abases
    -0.68
    POSITIVE LOGITS
    hovah
    0.81
    erness
    0.79
    staking
    0.77
    terday
    0.73
    joy
    0.71
    aughs
    0.69
    issan
    0.68
    Laughs
    0.66
    itri
    0.65
    geoning
    0.64
    Act Density 0.045%

    No Known Activations