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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time spans or durations

    oai_token-act-pair · gpt-3.5-turbo

    references to long time periods or the concept of "decades."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vine
    -0.77
    press
    -0.61
    oke
    -0.61
    XT
    -0.60
    obo
    -0.60
    opter
    -0.59
     (+
    -0.59
     therefore
    -0.57
    uru
    -0.57
     Finished
    -0.56
    POSITIVE LOGITS
     decades
    3.45
     centuries
    2.70
     millennia
    2.51
     years
    2.17
     generations
    2.06
     decade
    1.97
     months
    1.67
    years
    1.64
    Years
    1.52
     century
    1.51
    Act Density 0.011%

    No Known Activations