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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" followed by verbs in infinitive form

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intentions or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.66
    listed
    -0.65
    nces
    -0.63
    soDeliveryDate
    -0.62
     Appears
    -0.60
    reports
    -0.58
    tesy
    -0.57
     Caption
    -0.57
    resy
    -0.57
    quickShipAvailable
    -0.56
    POSITIVE LOGITS
     maximize
    1.04
     achieve
    1.01
     avoid
    1.01
     compensate
    1.00
     defend
    1.00
     conserve
    1.00
     satisfy
    0.99
     minimize
    0.99
     fulfill
    0.96
     preserve
    0.96
    Act Density 0.972%

    No Known Activations