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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inclusion or integration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of incorporation or integration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pport
    -0.69
    ateur
    -0.61
     ende
    -0.60
    ranged
    -0.60
     rall
    -0.59
    ointment
    -0.58
    Uncommon
    -0.57
    ord
    -0.56
    ark
    -0.56
     tending
    -0.55
    POSITIVE LOGITS
     into
    2.18
     INTO
    1.93
     Into
    1.90
    into
    1.89
     onto
    1.55
    aneously
    0.84
     seamlessly
    0.84
    untarily
    0.80
    onto
    0.78
     deeper
    0.75
    Act Density 0.490%

    No Known Activations