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

    Neuronpedia

    INDEX
    Explanations

    references to receiving or subscribing to daily newsletters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of daily newsletters and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naire
    -0.77
     resemb
    -0.71
    naires
    -0.68
    artisan
    -0.68
     unilaterally
    -0.65
    onite
    -0.64
    quartered
    -0.63
     positively
    -0.61
     favorably
    -0.59
     concurrently
    -0.58
    POSITIVE LOGITS
     dose
    0.86
     newsletter
    0.85
     roundup
    0.84
    motion
    0.72
     reminder
    0.71
     email
    0.67
     recap
    0.66
     digest
    0.65
    Morning
    0.65
     Newsletter
    0.65
    Act Density 0.013%

    No Known Activations