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

    Neuronpedia

    INDEX
    Explanations

    promotional messages related to newsletters, subscriptions, and clubs

    oai_token-act-pair · gpt-3.5-turbo

    calls to subscribe or sign up for newsletters and clubs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unaccount
    -0.64
    lihood
    -0.60
     Klu
    -0.60
     conson
    -0.60
    beit
    -0.59
    cific
    -0.58
    pmwiki
    -0.58
     positives
    -0.58
    anz
    -0.56
    ersen
    -0.55
    POSITIVE LOGITS
     >>>
    0.68
    CLASS
    0.59
     subscribe
    0.57
    Intel
    0.56
    Learn
    0.55
    ``
    0.55
     Subscribe
    0.54
    smart
    0.54
    >>>
    0.53
    ILE
    0.53
    Act Density 0.102%

    No Known Activations