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

    Neuronpedia

    INDEX
    Explanations

    mentions of experts providing insights or opinions

    oai_token-act-pair · gpt-3.5-turbo

    references to experts in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mi
    -0.72
    forth
    -0.69
     Agric
    -0.66
     Territories
    -0.66
    ward
    -0.65
     Winged
    -0.64
     Decay
    -0.62
     Marathon
    -0.60
     Pyr
    -0.60
    OUT
    -0.60
    POSITIVE LOGITS
     experts
    1.03
    sonian
    0.93
     consulted
    0.91
    uggest
    0.90
     expert
    0.88
    urus
    0.88
    anooga
    0.87
    cius
    0.87
     Experts
    0.86
    htaking
    0.86
    Act Density 0.011%

    No Known Activations