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

    Neuronpedia

    INDEX
    Explanations

    keywords related to submarines

    oai_token-act-pair · gpt-3.5-turbo

    references to submarines and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mel
    -0.83
    reet
    -0.74
    CLOSE
    -0.73
    iot
    -0.73
    walker
    -0.72
    aml
    -0.72
    ml
    -0.71
    emark
    -0.68
    han
    -0.68
     BET
    -0.67
    POSITIVE LOGITS
     submarines
    2.57
     submarine
    2.40
     subs
    1.57
     squid
    1.57
     submar
    1.57
     crabs
    1.52
     crab
    1.41
     Crab
    1.38
     torped
    1.23
     torpedo
    1.20
    Act Density 0.020%

    No Known Activations