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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of countries

    oai_token-act-pair · gpt-3.5-turbo

    references to policymakers and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ".
    -0.60
    +.
    -0.55
    $.
    -0.50
    livion
    -0.50
     equival
    -0.50
     approx
    -0.50
     allot
    -0.50
     ".
    -0.49
     goodbye
    -0.49
     eternity
    -0.49
    POSITIVE LOGITS
    pires
    0.71
     meanwhile
    0.62
    actionDate
    0.61
     interviewed
    0.57
    etheless
    0.56
    published
    0.55
    osponsors
    0.55
     testified
    0.53
     countered
    0.52
     publishes
    0.52
    Act Density 0.892%

    No Known Activations