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

    Neuronpedia

    INDEX
    Explanations

    dates specified with the ordinal number ('th')

    oai_token-act-pair · gpt-3.5-turbo

    ordinal and cardinal numbers related to dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbuds
    -0.70
     predec
    -0.60
    acci
    -0.59
    illas
    -0.58
     tame
    -0.56
    =-=-=-=-=-=-=-=-
    -0.56
     synonymous
    -0.56
     transact
    -0.56
     streng
    -0.55
     herds
    -0.55
    POSITIVE LOGITS
    ioxide
    0.91
    endment
    0.85
    ulhu
    0.84
     2018
    0.82
    ruary
    0.80
     onwards
    0.79
     2017
    0.75
     Amendment
    0.75
    rum
    0.74
     Anniversary
    0.73
    Act Density 0.020%

    No Known Activations