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

    Neuronpedia

    INDEX
    Explanations

    time-related events indicated by words such as days of the week and months

    oai_token-act-pair · gpt-3.5-turbo

    references to meetings and conferences involving officials or diplomats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qus
    -0.79
     cop
    -0.67
     subtract
    -0.66
    usercontent
    -0.65
     subdiv
    -0.64
     worms
    -0.64
     contribut
    -0.64
     chloride
    -0.63
     brakes
    -0.63
    é»Ĵ
    -0.62
    POSITIVE LOGITS
     chaired
    1.02
     keynote
    0.88
     briefed
    0.85
     convened
    0.82
    minster
    0.80
     seminars
    0.80
     briefing
    0.75
    morning
    0.75
     Downing
    0.74
    conference
    0.74
    Act Density 0.544%

    No Known Activations