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

    Neuronpedia

    INDEX
    Explanations

    mentions of people holding presidential or leadership positions

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worn
    -0.78
    placed
    -0.72
    aeus
    -0.67
    BER
    -0.66
    Wik
    -0.64
    arella
    -0.64
    reve
    -0.63
    arten
    -0.63
    fried
    -0.62
    BIL
    -0.62
    POSITIVE LOGITS
     aforementioned
    0.90
     latter
    0.83
     country
    0.81
     Americas
    0.80
     infamous
    0.79
     highest
    0.79
     planet
    0.74
     nation
    0.74
     respective
    0.73
     largest
    0.73
    Act Density 0.185%

    No Known Activations