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

    Neuronpedia

    INDEX
    Explanations

    phrases related to email subscriptions and newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription and acknowledgement of newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liest
    -0.87
    ÅŁ
    -0.70
    iod
    -0.67
    BACK
    -0.67
     Eleven
    -0.67
    lihood
    -0.64
     UD
    -0.63
     dissertation
    -0.63
    terness
    -0.62
    -----------
    -0.62
    POSITIVE LOGITS
     âĿ
    0.73
    Buyable
    0.70
     unlocks
    0.68
    Want
    0.68
    Sorry
    0.67
     gladly
    0.65
    Subscribe
    0.65
    selves
    0.63
     Email
    0.62
    avascript
    0.62
    Act Density 0.024%

    No Known Activations