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

    Neuronpedia

    INDEX
    Explanations

    highly frequent proper nouns or entities, especially with repeating patterns in their names

    oai_token-act-pair · gpt-3.5-turbo

    references to various media entities and news sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deduct
    -0.74
     additionally
    -0.73
     craw
    -0.73
     dece
    -0.71
     tram
    -0.70
     triv
    -0.69
     bundled
    -0.69
     larvae
    -0.68
     princ
    -0.68
     aggreg
    -0.67
    POSITIVE LOGITS
    Dear
    1.29
    Former
    1.23
    SAN
    1.21
    LOS
    1.20
    WASHINGTON
    1.20
    Published
    1.18
    When
    1.15
    If
    1.14
    Whether
    1.14
    TOR
    1.14
    Act Density 0.208%

    No Known Activations