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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts for asking questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccording
    -0.69
    pite
    -0.69
    accompan
    -0.67
    Ĥ¬
    -0.67
    cutting
    -0.67
    audi
    -0.67
    EStreamFrame
    -0.66
     Tigers
    -0.66
     Nanto
    -0.64
    Charge
    -0.63
    POSITIVE LOGITS
     rhet
    1.07
     questions
    0.94
    naires
    0.90
     asked
    0.86
    govtrack
    0.86
     probing
    0.83
     ask
    0.83
    FontSize
    0.80
    ingly
    0.78
     politely
    0.77
    Act Density 0.038%

    No Known Activations