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

    Neuronpedia

    INDEX
    Explanations

    references to shipwrecks and maritime disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¨İ
    -0.15
    plier
    -0.14
     Marina
    -0.14
    วà¸ĩศ
    -0.14
     nackt
    -0.14
    pliers
    -0.13
    lant
    -0.13
    eltas
    -0.13
    cone
    -0.13
     Deployment
    -0.13
    POSITIVE LOGITS
     wreck
    0.36
     sunk
    0.36
     sank
    0.35
     sink
    0.35
     sinking
    0.35
     sinks
    0.32
     wre
    0.31
    sink
    0.29
     caps
    0.28
    Sink
    0.28
    Act Density 0.073%

    No Known Activations