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

    Neuronpedia

    INDEX
    Explanations

    dates and events being announced

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to official announcements or disclosures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gencies
    -0.63
    mia
    -0.62
     coli
    -0.61
     recourse
    -0.60
     disob
    -0.60
    istries
    -0.59
    govtrack
    -0.58
    pi
    -0.57
    76561
    -0.56
    atin
    -0.56
    POSITIVE LOGITS
     onstage
    0.88
    daq
    0.85
    uled
    0.83
     earlier
    0.80
     publicly
    0.79
     yesterday
    0.78
     officially
    0.76
     beforehand
    0.76
     via
    0.75
     exclusively
    0.75
    Act Density 0.096%

    No Known Activations