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

    references to newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pex
    -0.64
    lly
    -0.61
    gn
    -0.61
     Shack
    -0.61
    iture
    -0.57
    mur
    -0.57
     Lam
    -0.57
    AGES
    -0.56
    builders
    -0.55
    Benz
    -0.55
    POSITIVE LOGITS
    interstitial
    0.90
     newsletters
    0.69
     externalToEVAOnly
    0.67
    padding
    0.66
     Email
    0.64
    ļéĨĴ
    0.64
    isodes
    0.64
     Continue
    0.62
    isode
    0.62
    nesday
    0.62
    Act Density 0.011%

    No Known Activations