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

    Neuronpedia

    INDEX
    Explanations

    date periods, historical contexts, or sequences of time

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.67
    Rus
    -0.66
    birds
    -0.66
    Fly
    -0.64
    ÄŁ
    -0.64
    Stars
    -0.63
    iants
    -0.62
    Row
    -0.61
    Train
    -0.61
     Aires
    -0.61
    POSITIVE LOGITS
    icals
    1.51
    icity
    1.38
    ical
    1.26
    ftime
    0.96
    ional
    0.94
    iday
    0.90
    ically
    0.90
     periods
    0.89
    ont
    0.85
    ozo
    0.84
    Act Density 0.045%

    No Known Activations