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

    Neuronpedia

    INDEX
    Explanations

    mentions of submarines

    oai_token-act-pair · gpt-3.5-turbo

    references to submarines and submarine-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.79
    cb
    -0.73
    grain
    -0.73
    Raw
    -0.71
    None
    -0.71
     Marketable
    -0.70
    giving
    -0.70
    ellen
    -0.69
    tg
    -0.69
    reads
    -0.68
    POSITIVE LOGITS
     submarine
    1.31
     submarines
    1.27
     submar
    1.22
    marine
    1.04
     submer
    0.96
     torped
    0.89
    iltration
    0.88
     diving
    0.88
    boats
    0.86
     submerged
    0.85
    Act Density 0.005%

    No Known Activations