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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns 'us' and 'we'

    oai_token-act-pair · gpt-3.5-turbo

    references to a collective group of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ATF
    -0.71
     Sale
    -0.67
     Arpaio
    -0.65
    ciation
    -0.65
    Offic
    -0.62
     Compliance
    -0.62
    Catalog
    -0.62
     Beckham
    -0.61
    division
    -0.58
    Constructed
    -0.58
    POSITIVE LOGITS
    hers
    0.98
    leep
    0.93
    imei
    0.83
     owe
    0.82
    uscript
    0.81
    ern
    0.81
     fathers
    0.80
    azeera
    0.76
    selves
    0.75
    algia
    0.75
    Act Density 0.038%

    No Known Activations