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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating preference, enjoyment, or worth in an activity

    oai_token-act-pair · gpt-3.5-turbo

    the infinitive form of verbs, particularly the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.74
     cords
    -0.62
     vi
    -0.61
    riot
    -0.61
     pledges
    -0.59
     warranties
    -0.59
     VAT
    -0.59
    letters
    -0.59
     Required
    -0.58
     surges
    -0.57
    POSITIVE LOGITS
     cherish
    1.14
    ggles
    1.13
    ying
    1.01
    wered
    0.96
    ller
    0.93
     consume
    0.92
    pper
    0.91
    ilet
    0.90
    cca
    0.90
     visualize
    0.90
    Act Density 0.153%

    No Known Activations