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

    Neuronpedia

    INDEX
    Explanations

    references to submarines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of submarines and related naval terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eful
    -0.85
    ellen
    -0.81
    reads
    -0.80
    iard
    -0.78
    grain
    -0.77
    tg
    -0.76
    âķIJâķIJ
    -0.74
    giving
    -0.74
    anza
    -0.73
    place
    -0.72
    POSITIVE LOGITS
     submarines
    1.00
     submarine
    1.00
    iltration
    0.94
     submar
    0.89
    marine
    0.83
     landsl
    0.83
     submerged
    0.79
     platoon
    0.78
     dug
    0.78
     cables
    0.78
    Act Density 0.013%

    No Known Activations