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

    Neuronpedia

    INDEX
    Explanations

    titles or positions of authority

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Joined
    -0.67
     opting
    -0.65
     spilling
    -0.64
    worn
    -0.64
     emphas
    -0.62
     because
    -0.62
    etheless
    -0.62
    anism
    -0.62
     underwent
    -0.61
     whenever
    -0.61
    POSITIVE LOGITS
     aforementioned
    1.05
     latter
    0.89
     respective
    0.84
     largest
    0.83
     Americas
    0.82
     United
    0.79
     infamous
    0.79
     same
    0.78
     nation
    0.78
     smallest
    0.77
    Act Density 0.129%

    No Known Activations