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

    Neuronpedia

    INDEX
    Explanations

    mentions of public opinion polls

    oai_token-act-pair · gpt-3.5-turbo

    references to polling data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -1.05
    complex
    -0.86
    EngineDebug
    -0.85
     Leilan
    -0.83
    Merit
    -0.76
     Protocol
    -0.74
     Caribbean
    -0.73
     Flavor
    -0.71
    minecraft
    -0.70
    ĨĴ
    -0.69
    POSITIVE LOGITS
     polls
    1.11
     polling
    1.10
    sters
    0.96
    hel
    0.87
    heet
    0.84
     booths
    0.78
     wat
    0.78
    hare
    0.77
     averages
    0.77
    inators
    0.76
    Act Density 0.027%

    No Known Activations