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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "since" used to indicate time or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.79
    abus
    -0.75
    agy
    -0.71
    potion
    -0.69
    BILITIES
    -0.65
    oqu
    -0.63
    Uncommon
    -0.62
    anie
    -0.62
    arnaev
    -0.61
    ucker
    -0.60
    POSITIVE LOGITS
     inception
    0.97
    rely
    0.96
     October
    0.83
     1954
    0.78
     infancy
    0.78
     August
    0.77
     afar
    0.77
     1952
    0.77
     1946
    0.77
     1951
    0.76
    Act Density 0.045%

    No Known Activations