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

    Neuronpedia

    INDEX
    Explanations

    mentions of election polls

    oai_token-act-pair · gpt-3.5-turbo

    references to polling data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.93
     Caribbean
    -0.81
    complex
    -0.80
     Protocol
    -0.76
    EngineDebug
    -0.75
    ahime
    -0.74
     Leilan
    -0.74
    uria
    -0.72
    Interstitial
    -0.71
     Flavor
    -0.69
    POSITIVE LOGITS
     polls
    1.14
     polling
    1.12
    sters
    0.85
     wat
    0.82
     poll
    0.81
    hare
    0.80
    dogs
    0.80
     handic
    0.79
    heet
    0.79
     canv
    0.79
    Act Density 0.014%

    No Known Activations