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

    Neuronpedia

    INDEX
    Explanations

    specific time frames in the near future

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a future timeframe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bley
    -0.69
     viol
    -0.63
    ollower
    -0.62
    osure
    -0.61
     Column
    -0.60
    eele
    -0.60
    paio
    -0.59
     Seat
    -0.59
    nces
    -0.59
    enf
    -0.58
    POSITIVE LOGITS
     generations
    0.98
    ebin
    0.91
     decade
    0.90
     millenn
    0.88
     millennia
    0.87
     timeframe
    0.80
     period
    0.79
     decades
    0.78
     Palestin
    0.77
     centuries
    0.76
    Act Density 0.056%

    No Known Activations