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

    Neuronpedia

    INDEX
    Explanations

    references to specific ages and time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to age and time-related details in contextual narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.61
    icultural
    -0.61
     stray
    -0.59
    zees
    -0.58
    ttes
    -0.58
    untled
    -0.57
    ancial
    -0.57
    MEN
    -0.57
     attendant
    -0.57
    ots
    -0.56
    POSITIVE LOGITS
     times
    1.09
     time
    0.95
     outset
    0.92
     inception
    0.84
    times
    0.79
     beginning
    0.77
     dawn
    0.76
     1900
    0.76
     moment
    0.75
     1920
    0.73
    Act Density 0.258%

    No Known Activations