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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LEASE
    -0.79
    undai
    -0.70
     referen
    -0.68
    ggle
    -0.66
    minus
    -0.66
    ccording
    -0.64
    untled
    -0.64
    Requirements
    -0.62
     Pradesh
    -0.62
    urities
    -0.62
    POSITIVE LOGITS
     Jr
    1.09
     III
    1.06
     QC
    1.00
    gren
    0.96
     aka
    0.90
     Sr
    0.86
    hurst
    0.86
    worth
    0.84
    etti
    0.83
     IV
    0.83
    Act Density 0.218%

    No Known Activations