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

    Neuronpedia

    INDEX
    Explanations

    marketing phrases related to subscription, errors, and newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription confirmations or acknowledgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ographed
    -0.66
    naire
    -0.59
     scen
    -0.59
    fters
    -0.58
     concussion
    -0.58
    ouf
    -0.53
    oshenko
    -0.52
     Henderson
    -0.52
    ufact
    -0.52
    ¯
    -0.51
    POSITIVE LOGITS
     subscribing
    0.62
    utenberg
    0.61
    interstitial
    0.60
    aston
    0.55
    Subscribe
    0.54
    bet
    0.53
    OTAL
    0.52
    Morning
    0.52
     Pandora
    0.52
    tmp
    0.52
    Act Density 0.043%

    No Known Activations