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

    Neuronpedia

    INDEX
    Explanations

    words related to future plans or goals

    oai_token-act-pair · gpt-3.5-turbo

    references to "vision," particularly in a planning or conceptual context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avis
    -0.82
    atern
    -0.77
    cold
    -0.70
    nie
    -0.69
    avez
    -0.68
    andise
    -0.67
    adding
    -0.67
    tha
    -0.67
    agher
    -0.65
    big
    -0.65
    POSITIVE LOGITS
     vision
    1.29
     visions
    1.10
     visionary
    0.93
     Vision
    0.86
    aries
    0.86
     goggles
    0.77
    Vision
    0.72
    naire
    0.71
     Lisbon
    0.66
     impaired
    0.66
    Act Density 0.011%

    No Known Activations