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

    Neuronpedia

    INDEX
    Explanations

    words related to the foundational or originating source of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "root" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.88
    ammy
    -0.86
    merce
    -0.83
    ourgeois
    -0.82
    vernment
    -0.80
    ramid
    -0.79
    psey
    -0.78
     disadvant
    -0.76
    ussian
    -0.76
    dinand
    -0.75
    POSITIVE LOGITS
     root
    1.14
    root
    0.94
     rooting
    0.92
     cellar
    0.88
    kit
    0.86
     Root
    0.84
    Root
    0.82
     roots
    0.81
    roots
    0.76
    cake
    0.75
    Act Density 0.004%

    No Known Activations