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

    Neuronpedia

    INDEX
    Explanations

    mentions of people being questioned or accused by authorities

    oai_token-act-pair · gpt-3.5-turbo

    articles used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    blocks
    -0.82
    Contents
    -0.82
    words
    -0.81
    anism
    -0.79
    izations
    -0.79
    flows
    -0.78
    thumbnails
    -0.78
    files
    -0.78
     arrangements
    -0.78
    orders
    -0.77
    POSITIVE LOGITS
     woman
    1.20
     colleague
    1.19
     friend
    1.11
     handful
    1.06
     dozen
    1.06
     fellow
    1.05
     bunch
    1.03
     stranger
    1.03
     guy
    1.03
     psychiatrist
    1.01
    Act Density 0.280%

    No Known Activations