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

    Neuronpedia

    INDEX
    Explanations

    references to various locations or regions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "across" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nery
    -0.81
    nel
    -0.71
    IZ
    -0.69
    etic
    -0.65
    zel
    -0.62
    anza
    -0.62
    nas
    -0.62
     diseng
    -0.60
     coincidence
    -0.60
    oka
    -0.59
    POSITIVE LOGITS
    roads
    1.09
    ĨĴ
    0.90
     disciplines
    0.84
    urst
    0.83
    cedented
    0.81
    artisan
    0.81
    scl
    0.79
    soType
    0.79
    atform
    0.76
    Ĥª
    0.75
    Act Density 0.025%

    No Known Activations