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

    Neuronpedia

    INDEX
    Explanations

    terms related to exchanges or swapping in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     carburant
    -0.93
     nationaux
    -0.80
     Moriarty
    -0.75
    ainville
    -0.75
    cetin
    -0.75
    }{||
    -0.75
    celotti
    -0.73
     defStyleAttr
    -0.73
    iverr
    -0.72
     jasper
    -0.72
    POSITIVE LOGITS
     Exchange
    1.83
     exchanges
    1.81
     exchange
    1.76
     EXCHANGE
    1.71
    Exchange
    1.70
    exchange
    1.67
     Exchanges
    1.61
     exchanged
    1.55
    EXCHANGE
    1.43
     exchanging
    1.39
    Act Density 0.077%

    No Known Activations