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

    Neuronpedia

    INDEX
    Explanations

    individuals' occupations and identities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating identity or characteristics of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    snap
    -0.74
    ipers
    -0.72
    ridges
    -0.70
    rates
    -0.68
    okes
    -0.67
    iasco
    -0.65
    ooters
    -0.65
    oos
    -0.63
    oks
    -0.62
    commit
    -0.62
    POSITIVE LOGITS
     flanked
    0.85
     currently
    0.84
     supposed
    0.83
     married
    0.83
     stationed
    0.79
     divorced
    0.76
     sworn
    0.76
     nearing
    0.76
     fluent
    0.76
     presently
    0.75
    Act Density 0.117%

    No Known Activations