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

    Neuronpedia

    INDEX
    Explanations

    expressions related to consulting doctors and healthcare advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plementation
    -0.14
    Ñĥв
    -0.14
    óz
    -0.14
    olate
    -0.14
     Mast
    -0.14
    (æĹ¥
    -0.13
    gaard
    -0.13
    egend
    -0.13
    ãģĿ
    -0.13
    jom
    -0.13
    POSITIVE LOGITS
     doctor
    0.68
     Doctor
    0.61
     doctors
    0.60
    doctor
    0.56
     physician
    0.53
    Doctor
    0.51
     physicians
    0.51
     doktor
    0.50
     Doctors
    0.49
     docs
    0.49
    Act Density 0.335%

    No Known Activations