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

    Neuronpedia

    INDEX
    Explanations

    references to impacted or vulnerable groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dumas
    -0.89
    jsonwebtoken
    -0.80
    ertos
    -0.72
    onucleotide
    -0.68
    rumah
    -0.68
     CYTHON
    -0.67
    writerow
    -0.66
     Wellesley
    -0.66
     Dumont
    -0.66
     useRouter
    -0.66
    POSITIVE LOGITS
     affected
    1.85
     AFFECT
    1.80
     affects
    1.77
     Affected
    1.74
     affecting
    1.73
     Affects
    1.71
     affect
    1.70
    affect
    1.66
    Affected
    1.61
     Affect
    1.59
    Act Density 0.114%

    No Known Activations