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

    Neuronpedia

    INDEX
    Explanations

    mentions of countries or geographic regions

    oai_token-act-pair · gpt-3.5-turbo

    references to international relations and geopolitical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oath
    -0.88
     aven
    -0.83
     pudding
    -0.82
     covenant
    -0.81
     screwed
    -0.77
     consum
    -0.77
     prosec
    -0.76
     enqu
    -0.75
     neglig
    -0.75
     abusing
    -0.75
    POSITIVE LOGITS
    Yet
    1.66
    But
    1.64
    Experts
    1.62
    However
    1.57
    Nevertheless
    1.56
    Recent
    1.55
    Researchers
    1.54
    Such
    1.53
    Others
    1.53
    Some
    1.52
    Act Density 0.394%

    No Known Activations