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

    Neuronpedia

    INDEX
    Explanations

    time-related information, especially years mentioned in a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.69
    ople
    -0.67
    achus
    -0.65
    ibrary
    -0.65
    eus
    -0.60
     VIDEOS
    -0.60
    urn
    -0.59
    ussed
    -0.59
    assium
    -0.59
    rotein
    -0.58
    POSITIVE LOGITS
     ago
    1.48
     Ago
    1.22
     olds
    1.21
    long
    1.03
     elapsed
    0.88
    ago
    0.82
     anniversary
    0.81
    iversary
    0.81
     old
    0.80
     hiatus
    0.78
    Act Density 2.443%

    No Known Activations