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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate professional experience and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asant
    -0.17
    antan
    -0.17
    аÑĢÑĮ
    -0.16
    adol
    -0.16
    ään
    -0.15
    theses
    -0.14
    aupt
    -0.14
    ney
    -0.14
    мени
    -0.14
    066
    -0.14
    POSITIVE LOGITS
     expertise
    0.20
     interests
    0.17
     responsibility
    0.16
    chte
    0.15
    kills
    0.15
     Responsibility
    0.14
    rál
    0.14
    lish
    0.14
     views
    0.14
    igs
    0.14
    Act Density 0.072%

    No Known Activations