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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of vessels, including ships and blood vessels

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of vessels, particularly in a medical or maritime context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.75
    enhagen
    -0.70
    iaries
    -0.68
    eyes
    -0.67
    andro
    -0.66
    -+-+-+-+
    -0.63
    mun
    -0.63
    clus
    -0.63
    iary
    -0.62
    ======
    -0.62
    POSITIVE LOGITS
     vessel
    1.25
     vessels
    1.17
     Vessel
    1.11
     HMS
    0.95
    wreck
    0.92
    wright
    0.89
     Titanic
    0.86
     USS
    0.83
     Yamato
    0.83
     ships
    0.80
    Act Density 0.014%

    No Known Activations