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

    Neuronpedia

    INDEX
    Explanations

    terms related to advocacy, activism, and social issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to formal procedures and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unst
    -0.62
     solicitor
    -0.61
     heterogeneity
    -0.58
    olyn
    -0.56
     narrowed
    -0.56
    ymm
    -0.56
    byn
    -0.54
    folio
    -0.54
     charism
    -0.53
    æĸ¹
    -0.53
    POSITIVE LOGITS
    ynthesis
    0.89
    udic
    0.75
    urized
    0.75
    eting
    0.74
    print
    0.73
    ibly
    0.73
    urable
    0.71
    netflix
    0.71
    eval
    0.70
    bol
    0.70
    Act Density 0.925%

    No Known Activations