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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific geopolitical entities or jurisdictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating states or conditions, particularly in political or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.73
    bley
    -0.71
    iator
    -0.65
     Cosponsors
    -0.65
     Telescope
    -0.63
    comed
    -0.63
    ÃŃs
    -0.62
     Zup
    -0.61
    <?
    -0.61
    poon
    -0.60
    POSITIVE LOGITS
     Decay
    0.77
    foundland
    0.77
     affairs
    0.75
    CLASSIFIED
    0.73
    IFIED
    0.71
    inence
    0.69
    ortunately
    0.65
    rency
    0.65
    vironment
    0.65
    gain
    0.65
    Act Density 0.070%

    No Known Activations