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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of labor and job-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zac
    -0.17
    ide
    -0.16
    oph
    -0.14
    acs
    -0.14
    ged
    -0.14
    ANGED
    -0.14
    wit
    -0.14
    con
    -0.14
    iglia
    -0.14
    e
    -0.13
    POSITIVE LOGITS
    manship
    0.25
    stations
    0.24
    aday
    0.24
    bench
    0.24
    forces
    0.23
    loads
    0.22
    shops
    0.20
    horse
    0.20
    zeug
    0.19
    ign
    0.19
    Act Density 0.162%

    No Known Activations