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

    Neuronpedia

    INDEX
    Explanations

    instances related to time that occur in the future

    oai_token-act-pair · gpt-3.5-turbo

    references to events or actions that happen subsequently, often indicated by the word "later."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ble
    -0.86
    emen
    -0.70
    eting
    -0.67
    mad
    -0.66
    washing
    -0.63
     Pwr
    -0.63
    hab
    -0.62
     Cause
    -0.61
    Unt
    -0.61
    cking
    -0.61
    POSITIVE LOGITS
     confir
    0.79
     iterations
    0.78
    iations
    0.77
    noon
    0.77
     succumb
    0.75
     recons
    0.72
     satell
    0.72
     generations
    0.71
     succumbed
    0.71
     regretted
    0.71
    Act Density 0.032%

    No Known Activations