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

    Neuronpedia

    INDEX
    Explanations

    calls to action or information requests in comments sections

    oai_token-act-pair · gpt-3.5-turbo

    prompts for audience engagement and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.79
    BuyableInstoreAndOnline
    -0.71
    cffffcc
    -0.66
    CONCLUS
    -0.64
    runs
    -0.64
    Traditional
    -0.62
    rawdownloadcloneembedreportprint
    -0.61
    Imm
    -0.61
    calling
    -0.60
    Mask
    -0.60
    POSITIVE LOGITS
     sugg
    0.90
     yourself
    0.84
     yourselves
    0.84
     feedback
    0.76
     Feedback
    0.76
     ASAP
    0.73
     responsibly
    0.72
     moderator
    0.71
     answ
    0.69
     wisely
    0.68
    Act Density 0.258%

    No Known Activations