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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cleaning or tidying up

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cleaning or correcting past mistakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enza
    -0.75
    yip
    -0.73
    nostic
    -0.73
    ratulations
    -0.72
    isSpecialOrderable
    -0.71
    nir
    -0.67
    ĸļ
    -0.66
    ait
    -0.64
    option
    -0.64
     pairing
    -0.64
    POSITIVE LOGITS
     polluted
    1.04
     dishes
    1.03
     toilets
    1.02
     mess
    1.00
     wounds
    0.96
     stains
    0.94
     spills
    0.91
     floors
    0.88
     ruins
    0.86
     contaminated
    0.84
    Act Density 0.112%

    No Known Activations