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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal systems and laws

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arten
    -0.80
    arella
    -0.75
    etsk
    -0.75
    pload
    -0.71
     furthermore
    -0.68
    illion
    -0.67
    fulness
    -0.67
     thereof
    -0.64
    hari
    -0.64
    aciously
    -0.64
    POSITIVE LOGITS
     aforementioned
    1.01
     latter
    0.99
     same
    0.95
     smallest
    0.92
     utmost
    0.87
     entire
    0.86
     slightest
    0.85
     respective
    0.83
     greatest
    0.82
     highest
    0.82
    Act Density 0.345%

    No Known Activations