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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the passage of time since a specific event or action occurred

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.82
    asio
    -0.58
    edience
    -0.57
    ingu
    -0.57
    aires
    -0.57
    aneously
    -0.57
    lect
    -0.57
    acion
    -0.56
    Weapon
    -0.56
    first
    -0.56
    POSITIVE LOGITS
     awhile
    1.34
     raining
    0.97
     decades
    0.88
     speculated
    0.88
     months
    0.86
     years
    0.86
     downhill
    0.85
     ages
    0.84
     rumored
    0.82
     YEAR
    0.82
    Act Density 0.055%

    No Known Activations