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

    Neuronpedia

    INDEX
    Explanations

    references to political representatives and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooth
    -0.17
    ryn
    -0.15
    ry
    -0.14
    eru
    -0.14
    -0.14
    è¶
    -0.13
    eller
    -0.13
    owan
    -0.13
    goo
    -0.13
    plex
    -0.13
    POSITIVE LOGITS
    .).↵↵
    0.15
    INET
    0.15
    /Private
    0.14
    GenerationStrategy
    0.14
    ï¸ı
    0.14
    .,
    0.14
    ippet
    0.14
    ettel
    0.14
    ä¹Ī
    0.13
    OffsetTable
    0.13
    Act Density 0.138%

    No Known Activations