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

    Neuronpedia

    INDEX
    Explanations

    mentions of salaries or payments

    oai_token-act-pair · gpt-3.5-turbo

    references to pay and salary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GGGGGGGG
    -0.83
    _>
    -0.81
    âĸ¬
    -0.80
    ARGET
    -0.73
    EStream
    -0.70
     Archdemon
    -0.68
    FTWARE
    -0.66
    ãĥķ
    -0.66
     Uriel
    -0.66
     Scotia
    -0.65
    POSITIVE LOGITS
    checks
    1.39
    outs
    1.23
    roll
    1.05
    offs
    1.03
    paying
    0.91
    back
    0.91
    rites
    0.90
    ments
    0.90
    pal
    0.90
    paid
    0.89
    Act Density 0.032%

    No Known Activations