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

    Neuronpedia

    INDEX
    Explanations

    references to subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    mentions or references to newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jury
    -0.72
    come
    -0.68
    phant
    -0.67
    FER
    -0.65
    government
    -0.63
    phal
    -0.63
    bang
    -0.63
    private
    -0.62
    ple
    -0.62
    aneous
    -0.62
    POSITIVE LOGITS
     subscriptions
    1.08
     newsletters
    1.07
     newsletter
    1.04
     subscribers
    1.02
     inbox
    0.98
     Seym
    0.97
     subscription
    0.87
    ļéĨĴ
    0.87
     Newsletter
    0.86
     Subscribe
    0.85
    Act Density 0.010%

    No Known Activations