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

    Neuronpedia

    INDEX
    Explanations

    words related to borrowing or names including "Lor"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific names and references to boredom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ted
    -0.88
    eers
    -0.78
    ulate
    -0.77
    ilus
    -0.77
    hered
    -0.76
    paio
    -0.75
    cius
    -0.75
    ulates
    -0.73
    erate
    -0.72
    ichick
    -0.71
    POSITIVE LOGITS
    hood
    0.79
    ussia
    0.73
    iculture
    0.70
    atively
    0.69
    atives
    0.68
    OUGH
    0.68
    UST
    0.68
    asta
    0.68
    ingo
    0.67
     Adin
    0.64
    Act Density 0.090%

    No Known Activations