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

    Neuronpedia

    INDEX
    Explanations

    references to vehicle performance modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilim
    -0.18
     Elastic
    -0.15
    /embed
    -0.15
     Immutable
    -0.14
     pokoj
    -0.14
     Gerr
    -0.14
    bet
    -0.14
    æı
    -0.14
    åµ
    -0.14
    parate
    -0.14
    POSITIVE LOGITS
     stock
    0.28
     OE
    0.27
     bil
    0.23
    Stock
    0.23
     Stock
    0.23
    -stock
    0.23
    factory
    0.23
     Jeg
    0.22
     Factory
    0.21
     factory
    0.21
    Act Density 0.186%

    No Known Activations