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

    Neuronpedia

    INDEX
    Explanations

    references to political parties and electoral outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ildo
    -0.16
    _rq
    -0.15
    ronics
    -0.14
    κÏģα
    -0.14
    amac
    -0.14
    ango
    -0.14
    rowsers
    -0.13
     republik
    -0.13
    atus
    -0.13
    RAND
    -0.13
    POSITIVE LOGITS
     Lib
    0.32
     Lab
    0.31
     Tory
    0.28
     Labour
    0.28
     LAB
    0.27
     SNP
    0.27
     Tories
    0.26
     seats
    0.25
     Conservatives
    0.24
    Lab
    0.24
    Act Density 0.019%

    No Known Activations