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

    Neuronpedia

    INDEX
    Explanations

    words related to belief or faith

    oai_token-act-pair · gpt-3.5-turbo

    the presence of variations of the word "beef."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )=(
    -0.69
    =-=-=-=-
    -0.67
     Passenger
    -0.63
     bear
    -0.59
    âĸ¬
    -0.59
    FTWARE
    -0.59
    âĶģ
    -0.58
     ply
    -0.57
     Poles
    -0.57
    git
    -0.57
    POSITIVE LOGITS
    icient
    1.21
    inition
    1.19
    orce
    1.13
    riend
    1.08
    onso
    1.08
    ield
    1.02
    ornia
    0.99
    ault
    0.98
    aq
    0.97
    iciency
    0.97
    Act Density 0.017%

    No Known Activations