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

    Neuronpedia

    INDEX
    Explanations

    dates expressed as day to day ranges

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orf
    -0.95
    anooga
    -0.92
     Hezbollah
    -0.87
    970
    -0.84
    173
    -0.78
     Tsuk
    -0.77
    orp
    -0.77
    tun
    -0.74
    Fin
    -0.74
     reluct
    -0.74
    POSITIVE LOGITS
    day
    1.61
     Day
    1.60
    Day
    1.54
     DAY
    1.52
    DAY
    1.49
     day
    1.48
     Days
    1.36
     days
    1.29
    Days
    1.23
    days
    1.20
    Act Density 0.168%

    No Known Activations