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

    Neuronpedia

    INDEX
    Explanations

    phrases related to signing up for services or newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing up for services or subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Galile
    -0.66
     Mous
    -0.66
     Gim
    -0.64
     Gunn
    -0.62
     delic
    -0.60
     gelatin
    -0.59
    grim
    -0.58
     cous
    -0.58
     bis
    -0.58
    iHUD
    -0.57
    POSITIVE LOGITS
    skirts
    0.90
    lish
    0.83
    à¼
    0.80
    ateful
    0.79
    shirts
    0.77
    adesh
    0.74
    ername
    0.72
    dates
    0.72
    swing
    0.69
     consent
    0.69
    Act Density 0.025%

    No Known Activations