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

    Neuronpedia

    INDEX
    Explanations

    European countries and US political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries in a geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.70
    ãĥ´
    -0.69
    ©¶æ
    -0.63
    )=
    -0.61
    mble
    -0.61
    ĨĴ
    -0.61
     pse
    -0.58
    Ļ½
    -0.58
    76561
    -0.57
    sembly
    -0.57
    POSITIVE LOGITS
     anymore
    0.73
    's
    0.70
     altogether
    0.66
     because
    0.65
     bandwagon
    0.62
     anytime
    0.61
     whims
    0.61
    their
    0.61
    ÃŃs
    0.59
     looming
    0.58
    Act Density 0.974%

    No Known Activations