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

    Neuronpedia

    INDEX
    Explanations

    references to skills and knowledge related to cooking and sewing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     både
    -0.73
     both
    -0.71
     rather
    -0.68
    而不是
    -0.67
     plutôt
    -0.63
    而非
    -0.63
     istället
    -0.60
     almost
    -0.60
    rather
    -0.60
    both
    -0.58
    POSITIVE LOGITS
     nor
    2.27
     anymore
    2.09
     anything
    1.66
    nor
    1.53
     anywhere
    1.38
     tampoco
    1.38
     siquiera
    1.36
    anything
    1.36
     melainkan
    1.34
     nemmeno
    1.30
    Act Density 2.918%

    No Known Activations