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

    Neuronpedia

    INDEX
    Explanations

    phrases related to warnings and precautions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of pretense or straightforward communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.67
    alties
    -0.66
    nels
    -0.64
    arov
    -0.62
     lining
    -0.62
     Beir
    -0.61
    nell
    -0.59
    ussia
    -0.59
    netflix
    -0.58
    leton
    -0.57
    POSITIVE LOGITS
     disclaimer
    0.92
     recap
    0.91
     summar
    0.90
     summarize
    0.88
     briefly
    0.83
     reiterate
    0.83
     paraph
    0.80
     understatement
    0.79
     bre
    0.78
     rant
    0.78
    Act Density 0.623%

    No Known Activations