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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to life events and experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to personal life experiences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aye
    -0.92
     Cosponsors
    -0.79
    armed
    -0.68
     ratios
    -0.67
     EW
    -0.66
     Deadline
    -0.65
     attribution
    -0.65
    Rat
    -0.64
     Elk
    -0.64
    arms
    -0.64
    POSITIVE LOGITS
     shortened
    0.83
     glamorous
    0.82
     revolves
    0.82
     intertwined
    0.81
     ruined
    0.81
     adventures
    0.81
     whirlwind
    0.80
     adventure
    0.80
     forfeit
    0.79
     fortunes
    0.79
    Act Density 0.201%

    No Known Activations