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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    oai_token-act-pair · gpt-3.5-turbo

    references to time-sensitive information or deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     acronym
    -0.76
     Cosponsors
    -0.59
    ãĥĬ
    -0.56
    TextColor
    -0.55
    ãĥ¼ãĥĨãĤ£
    -0.53
    ãĤ¤ãĥĪ
    -0.53
    ħĭ
    -0.52
     moniker
    -0.51
     assassinated
    -0.51
    ="#
    -0.50
    POSITIVE LOGITS
    depending
    0.68
     depending
    0.60
     Dish
    0.52
     Plane
    0.52
     Sched
    0.52
    hooting
    0.50
     Directions
    0.50
     2019
    0.48
     Orders
    0.48
    gencies
    0.48
    Act Density 1.284%

    No Known Activations