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

    Neuronpedia

    INDEX
    Explanations

    references to roles or positions within a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exponent
    -0.17
     adviser
    -0.15
    ä¸ļ
    -0.15
     practitioner
    -0.15
     advisor
    -0.15
    aaS
    -0.15
     luk
    -0.15
    師
    -0.15
     lecturer
    -0.14
    æ¥Ń
    -0.14
    POSITIVE LOGITS
     HR
    0.32
     Marketing
    0.32
     Accounts
    0.31
     marketing
    0.30
    HR
    0.30
     Human
    0.28
     Operations
    0.28
     finance
    0.28
     reception
    0.28
     IT
    0.27
    Act Density 0.423%

    No Known Activations