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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of year followed by a non-zero activation value

    oai_token-act-pair · gpt-3.5-turbo

    specific years and notable historical dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    htaking
    -0.70
     TEXT
    -0.70
    EStreamFrame
    -0.65
     ancest
    -0.65
    abilia
    -0.61
     poster
    -0.61
    kef
    -0.58
     inhabit
    -0.58
    imate
    -0.57
     Num
    -0.55
    POSITIVE LOGITS
     onwards
    0.95
     onward
    0.91
     thereafter
    0.82
    theless
    0.74
    later
    0.72
    after
    0.69
    fml
    0.67
    iday
    0.66
     mornings
    0.66
    »Ĵ
    0.65
    Act Density 0.237%

    No Known Activations