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

    the conjunction "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ital
    -0.71
    banks
    -0.71
    ensus
    -0.70
    agog
    -0.69
    ourcing
    -0.69
    olutions
    -0.67
    aters
    -0.66
    iability
    -0.66
    doi
    -0.64
    codes
    -0.64
    POSITIVE LOGITS
     his
    1.13
     Associates
    1.03
     Sons
    0.91
     others
    0.90
     fellow
    0.88
     proceeded
    0.82
     His
    0.81
     thereby
    0.81
     assorted
    0.80
     her
    0.80
    Act Density 0.205%

    No Known Activations