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

    Neuronpedia

    INDEX
    Explanations

    mentions of laws or regulations being applied or discussed

    oai_token-act-pair · gpt-3.5-turbo

    the verb "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urry
    -0.74
    onso
    -0.71
    oire
    -0.71
    iates
    -0.70
    ossom
    -0.67
    ileaks
    -0.67
    icism
    -0.64
    ortmund
    -0.63
    ulus
    -0.62
    town
    -0.62
    POSITIVE LOGITS
    senal
    1.17
    wolves
    1.04
     hereby
    0.93
    wolf
    0.93
     supposed
    0.91
     not
    0.86
     usually
    0.84
     currently
    0.83
     generally
    0.82
     bound
    0.81
    Act Density 0.342%

    No Known Activations