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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years, particularly 2017 and 2018

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iques
    -0.75
    hiba
    -0.61
    cold
    -0.60
    nces
    -0.59
    imore
    -0.59
    xual
    -0.59
    avis
    -0.58
    immer
    -0.58
    ÃŃn
    -0.58
    olesterol
    -0.57
    POSITIVE LOGITS
    halla
    0.77
    ACA
    0.73
    WER
    0.71
     onwards
    0.68
    #$
    0.68
    âĢ³
    0.66
    /#
    0.66
    GMT
    0.64
     Winners
    0.63
     Remastered
    0.62
    Act Density 0.040%

    No Known Activations