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

    Neuronpedia

    INDEX
    Explanations

    website URLs

    oai_token-act-pair · gpt-3.5-turbo

    end of document markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cellence
    -0.79
    ortium
    -0.76
    table
    -0.68
    cientious
    -0.67
    =-=-=-=-
    -0.67
    peria
    -0.67
    ¶
    -0.66
    ionage
    -0.65
    ================================
    -0.64
    creen
    -0.64
    POSITIVE LOGITS
    acan
    0.77
    interstitial
    0.70
    ©¶æ¥µ
    0.68
    lde
    0.67
    ãĥ¼ãĥ³
    0.67
    ģ«
    0.67
    zens
    0.66
    ãĥ³
    0.65
    apple
    0.64
    arthed
    0.64
    Act Density 0.023%

    No Known Activations