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

    Neuronpedia

    INDEX
    Explanations

    references to the future

    oai_token-act-pair · gpt-3.5-turbo

    references to "the future"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lee
    -0.83
    Fat
    -0.78
    ety
    -0.77
    azines
    -0.77
    edin
    -0.74
    ECA
    -0.72
    ghan
    -0.72
    toe
    -0.71
    tha
    -0.71
    idelines
    -0.71
    POSITIVE LOGITS
     generations
    1.09
     occupant
    0.96
     prospects
    0.89
     horizon
    0.87
     outlook
    0.86
     occupants
    0.82
     tense
    0.82
     trajectory
    0.81
     generation
    0.80
     installments
    0.80
    Act Density 0.046%

    No Known Activations