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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "recently."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or recentness of events and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Timbers
    -0.71
     Ethiopian
    -0.64
     Braves
    -0.62
     Guatem
    -0.62
     Hond
    -0.61
     ANC
    -0.61
     bye
    -0.60
     Canucks
    -0.60
     Hawks
    -0.60
     Majority
    -0.60
    POSITIVE LOGITS
    sect
    0.83
    than
    0.82
    heed
    0.82
    developed
    0.79
    dated
    0.79
    defined
    0.78
    aching
    0.77
    mercial
    0.76
     than
    0.76
    interstitial
    0.75
    Act Density 0.086%

    No Known Activations