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

    Neuronpedia

    INDEX
    Explanations

    references to leadership positions and roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /cms
    -0.17
    523
    -0.15
    acher
    -0.15
     bic
    -0.15
    anter
    -0.14
    nd
    -0.14
     Metric
    -0.13
    ari
    -0.13
     Clamp
    -0.13
     ips
    -0.13
    POSITIVE LOGITS
     Weston
    0.16
    ostel
    0.16
    ships
    0.16
    warts
    0.15
    ält
    0.14
    rophe
    0.14
     Tart
    0.14
    radan
    0.14
    .Automation
    0.14
    Äįan
    0.14
    Act Density 0.011%

    No Known Activations