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

    Neuronpedia

    INDEX
    Explanations

    phrases related to receiving updates, offers, and promotions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to receiving updates and promotional offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.77
    pher
    -0.74
    geist
    -0.72
    stood
    -0.72
    had
    -0.71
    agate
    -0.70
    went
    -0.69
     Factor
    -0.69
     Eug
    -0.67
    lda
    -0.66
    POSITIVE LOGITS
     occasional
    1.00
     updates
    0.89
     notification
    0.89
     installments
    0.87
     periodic
    0.85
     recurring
    0.81
     snipp
    0.78
    interstitial
    0.78
    ãģı
    0.77
     notifications
    0.76
    Act Density 0.011%

    No Known Activations