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

    Neuronpedia

    INDEX
    Explanations

    phrases related to email newsletters and upgrades

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to newsletters and subscription prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.76
    olina
    -0.68
    eur
    -0.67
    0000000000000000
    -0.66
    clud
    -0.61
    nered
    -0.59
    abouts
    -0.58
    uci
    -0.58
    paces
    -0.57
    ppings
    -0.57
    POSITIVE LOGITS
    ochond
    0.62
    riter
    0.61
    inion
    0.59
     Brief
    0.59
    culosis
    0.57
    ments
    0.55
    qqa
    0.55
    etitive
    0.55
     Required
    0.54
    charged
    0.54
    Act Density 0.031%

    No Known Activations