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

    Neuronpedia

    INDEX
    Explanations

    references to waste and items that are discarded as rubbish

    oai_token-act-pair · gpt-3.5-turbo

    references to waste or trash

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akening
    -0.78
    ationally
    -0.69
    rared
    -0.69
    ulner
    -0.69
    iscopal
    -0.69
    MSN
    -0.68
    RL
    -0.67
    arine
    -0.66
    )=(
    -0.66
    ffield
    -0.66
    POSITIVE LOGITS
     cans
    1.05
     heap
    0.99
     dumps
    0.97
     bags
    0.93
    bags
    0.91
     disposal
    0.90
     bins
    0.90
    ãĤĵ
    0.88
     piles
    0.87
     recept
    0.86
    Act Density 0.024%

    No Known Activations