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

    Neuronpedia

    INDEX
    Explanations

    phrases related to signing up for newsletters or alerts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing up for newsletters or subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dest
    -0.60
     McMaster
    -0.58
     Keller
    -0.58
     torn
    -0.57
     Kats
    -0.57
    erves
    -0.57
    geries
    -0.55
     Galile
    -0.54
    heim
    -0.54
     barley
    -0.53
    POSITIVE LOGITS
    à¼
    0.79
    ratulations
    0.78
    ername
    0.73
    skirts
    0.72
    ateful
    0.65
    earable
    0.64
    Interstitial
    0.63
    puff
    0.62
    atalie
    0.61
     Thumbnails
    0.61
    Act Density 0.021%

    No Known Activations