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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs in the infinitive form indicating upcoming actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating plans or imminent actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Compass
    -0.82
     Corpus
    -0.66
     Gould
    -0.66
     Picks
    -0.65
    quickShipAvailable
    -0.65
     Akin
    -0.64
     Howe
    -0.63
     perce
    -0.62
     Sut
    -0.61
    iple
    -0.61
    POSITIVE LOGITS
    pless
    0.88
     rehe
    0.80
     make
    0.80
     give
    0.76
     be
    0.75
     confront
    0.73
     settle
    0.73
     indulge
    0.72
     fulfill
    0.71
     capitalize
    0.70
    Act Density 0.046%

    No Known Activations