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

    Neuronpedia

    INDEX
    Explanations

    timestamps or time-related information, specifically focusing on events that occurred a few weeks ago

    oai_token-act-pair · gpt-3.5-turbo

    mentions of time periods, specifically referencing the phrase "weeks ago."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lua
    -0.75
    eers
    -0.72
    ingham
    -0.71
    amins
    -0.71
    eer
    -0.70
    izoph
    -0.67
    ordes
    -0.65
    abilia
    -0.65
    anza
    -0.64
    Py
    -0.63
    POSITIVE LOGITS
    rolet
    0.87
     mornings
    0.84
    opausal
    0.80
     ago
    0.78
     afternoon
    0.72
    èª
    0.67
     evening
    0.65
     announcing
    0.63
     morning
    0.63
     sunset
    0.63
    Act Density 0.023%

    No Known Activations