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

    Neuronpedia

    INDEX
    Explanations

    references to political situations involving government shutdowns

    oai_token-act-pair · gpt-3.5-turbo

    references to government shutdowns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hart
    -0.78
    Adv
    -0.77
    aum
    -0.76
    Lev
    -0.75
    eva
    -0.73
    oeuv
    -0.73
    DN
    -0.73
    ---------------
    -0.72
    arist
    -0.69
    Digital
    -0.68
    POSITIVE LOGITS
     shutdown
    1.19
     aver
    0.91
     Shutdown
    0.90
     standoff
    0.82
     lockdown
    0.79
     showdown
    0.79
     Shut
    0.77
     shutter
    0.74
     timers
    0.73
     closures
    0.73
    Act Density 0.012%

    No Known Activations