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

    Neuronpedia

    INDEX
    Explanations

    topics related to education and learning

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups and categories of people or entities in a broad context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPA
    -0.75
    PDATE
    -0.71
    ATIONAL
    -0.69
    atorium
    -0.68
    CLASSIFIED
    -0.68
    ãĤ¦ãĤ¹
    -0.67
    âĸ¬
    -0.64
    Published
    -0.64
    yss
    -0.64
    athon
    -0.64
    POSITIVE LOGITS
    mith
    1.05
    hips
    1.02
    hip
    0.89
    poons
    0.84
    manship
    0.82
     piled
    0.82
    uits
    0.81
     abound
    0.78
    ystem
    0.78
    peed
    0.74
    Act Density 0.594%

    No Known Activations