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

    Neuronpedia

    INDEX
    Explanations

    expressions related to durations of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate duration or experience over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iru
    -0.66
     constitu
    -0.61
    kt
    -0.60
    GAME
    -0.59
    morrow
    -0.59
    estamp
    -0.58
    aturday
    -0.58
    abus
    -0.57
     horizont
    -0.56
     awoke
    -0.56
    POSITIVE LOGITS
     decades
    1.20
     thirty
    1.06
     25
    1.04
     seventeen
    1.04
     35
    1.03
     twenty
    1.00
     thirteen
    1.00
     nineteen
    0.98
     decade
    0.98
     eight
    0.97
    Act Density 0.152%

    No Known Activations