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

    Neuronpedia

    INDEX
    Explanations

    keywords related to news and current events, including locations, political actions, and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used in various contexts indicating comparisons or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minus
    -0.73
    LESS
    -0.67
    ivas
    -0.66
    itiveness
    -0.66
    eeee
    -0.65
    audi
    -0.64
    itatively
    -0.64
    files
    -0.63
    romy
    -0.62
    lor
    -0.62
    POSITIVE LOGITS
    pires
    0.92
    pired
    0.91
    piring
    0.89
    pects
    0.88
    piration
    0.88
     opposed
    0.85
    phy
    0.85
     soon
    0.84
     well
    0.84
    ynchron
    0.83
    Act Density 0.197%

    No Known Activations