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

    Neuronpedia

    INDEX
    Explanations

    phrases related to notable individuals

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" appearing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eno
    -0.74
    thood
    -0.69
    verage
    -0.65
    IRO
    -0.64
    />
    -0.63
    ency
    -0.62
    ����
    -0.62
    orate
    -0.61
    incent
    -0.61
     throughout
    -0.60
    POSITIVE LOGITS
     oldest
    1.10
     largest
    1.02
     youngest
    1.01
     latter
    1.00
     biggest
    0.95
     smallest
    0.93
     longest
    0.93
     aforementioned
    0.93
     earliest
    0.91
     fastest
    0.89
    Act Density 0.171%

    No Known Activations