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

    Neuronpedia

    INDEX
    Explanations

    specific mention of individuals performing work-related activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "worked for" followed by a numeric value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.73
    Ire
    -0.70
    clair
    -0.67
    801
    -0.66
    heart
    -0.65
    plate
    -0.65
    ãĥīãĥ©
    -0.65
    REDACTED
    -0.63
    illin
    -0.63
    Strange
    -0.62
    POSITIVE LOGITS
    geries
    0.96
    gotten
    0.96
     hire
    0.94
    bidden
    0.84
    ividual
    0.84
     instance
    0.82
     example
    0.81
     awhile
    0.77
    ays
    0.75
    gery
    0.75
    Act Density 0.124%

    No Known Activations