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

    Neuronpedia

    INDEX
    Explanations

    references to professionalism or professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qid
    -0.15
    illard
    -0.15
    nik
    -0.15
    eners
    -0.14
     Sab
    -0.14
    iper
    -0.14
    aul
    -0.14
    éĺµ
    -0.14
    are
    -0.14
    ocator
    -0.14
    POSITIVE LOGITS
    ise
    0.21
    -grade
    0.18
    anter
    0.16
     Boeh
    0.15
    -government
    0.15
    istic
    0.14
    OMEM
    0.14
    ouz
    0.14
    voke
    0.14
    typ
    0.14
    Act Density 0.019%

    No Known Activations