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

    Neuronpedia

    INDEX
    Explanations

    time indicators or durations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "since" used to indicate a duration of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bart
    -0.75
    pta
    -0.70
    amina
    -0.70
    abus
    -0.70
    Fight
    -0.69
    NRS
    -0.67
    agy
    -0.66
    BILITIES
    -0.63
    fighter
    -0.61
    amount
    -0.61
    POSITIVE LOGITS
    rely
    1.13
    ĸļ
    1.04
     inception
    0.79
     adolescence
    0.74
     1979
    0.74
     childhood
    0.73
     endorsing
    0.72
     1945
    0.72
     infancy
    0.71
     2006
    0.71
    Act Density 0.049%

    No Known Activations