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

    Neuronpedia

    INDEX
    Explanations

    mentions of the political party "Labor"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Labor Party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irs
    -0.79
    imaru
    -0.75
    mares
    -0.66
    irin
    -0.66
     KD
    -0.65
     Allaah
    -0.64
     Roche
    -0.62
     Hiroshima
    -0.62
    posts
    -0.61
    laus
    -0.60
    POSITIVE LOGITS
     Labor
    0.84
    aby
    0.80
     unions
    0.79
    Union
    0.76
    Labor
    0.73
    acia
    0.72
    union
    0.72
    Care
    0.66
    Leaks
    0.66
     Workers
    0.66
    Act Density 0.012%

    No Known Activations