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

    Neuronpedia

    INDEX
    Explanations

    terms related to cleaning activities

    oai_token-act-pair · gpt-3.5-turbo

    references to cleaning activities or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.96
    think
    -0.70
    uld
    -0.69
    aji
    -0.69
    sson
    -0.68
     Osw
    -0.66
    CVE
    -0.65
    pton
    -0.64
     Palin
    -0.64
    ensical
    -0.63
    POSITIVE LOGITS
     cleaner
    0.89
    liness
    0.83
     Clean
    0.82
     ashore
    0.79
     cleaners
    0.77
    clean
    0.76
    ãĤĵ
    0.76
    Clean
    0.75
     cleaning
    0.69
     clears
    0.68
    Act Density 0.025%

    No Known Activations