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

    Neuronpedia

    INDEX
    Explanations

    text related to subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to newsletter subscriptions and sign-up prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abal
    -0.77
    pex
    -0.77
    iddles
    -0.69
    imgur
    -0.66
     Loki
    -0.66
    emale
    -0.63
    itives
    -0.63
    ovember
    -0.60
    vironments
    -0.60
    argon
    -0.59
    POSITIVE LOGITS
     subclass
    0.61
    interstitial
    0.61
     Cancel
    0.60
     {*
    0.59
    scill
    0.59
    gdala
    0.57
     titled
    0.55
     alerts
    0.55
     entit
    0.54
     subscrib
    0.54
    Act Density 0.025%

    No Known Activations