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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and international relations terms

    oai_token-act-pair · gpt-3.5-turbo

    geopolitical references and country-specific information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.67
     incent
    -0.60
     suffice
    -0.59
     OCD
    -0.59
     novelty
    -0.58
     oneself
    -0.58
     increments
    -0.56
     assum
    -0.55
     nausea
    -0.54
     predec
    -0.53
    POSITIVE LOGITS
    Population
    0.66
    quartered
    0.66
    aucuses
    0.65
     Confederation
    0.64
    icent
    0.61
     Population
    0.61
     abroad
    0.60
    ederation
    0.60
    Mexico
    0.59
     imports
    0.57
    Act Density 1.316%

    No Known Activations