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

    Neuronpedia

    INDEX
    Explanations

    references to political parties and their leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rok
    -0.17
     Consortium
    -0.17
    unci
    -0.15
     Conservative
    -0.15
    Licensed
    -0.15
     nackte
    -0.15
    Labor
    -0.15
     Labor
    -0.14
     bipartisan
    -0.14
    358
    -0.14
    POSITIVE LOGITS
     Party
    0.29
     leader
    0.24
     candidate
    0.23
     party
    0.23
    Party
    0.23
     PARTY
    0.22
     leadership
    0.20
     MP
    0.20
    -le
    0.20
    .party
    0.20
    Act Density 0.029%

    No Known Activations