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

    Neuronpedia

    INDEX
    Explanations

    statistics and polling data

    oai_token-act-pair · gpt-3.5-turbo

    statistical percentages related to survey results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     garg
    -0.73
    unct
    -0.71
    Redd
    -0.70
     prolifer
    -0.69
    uran
    -0.67
     subsequ
    -0.67
     Byz
    -0.65
     metast
    -0.64
    mone
    -0.64
     Flavoring
    -0.63
    POSITIVE LOGITS
     polled
    0.92
     respondents
    0.84
    percent
    0.81
     surveyed
    0.79
    votes
    0.78
     undecided
    0.77
    agree
    0.75
    %,
    0.73
     turnout
    0.70
     Gallup
    0.68
    Act Density 0.059%

    No Known Activations