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

    Neuronpedia

    INDEX
    Explanations

    titles or roles associated with assistant positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vertx
    -0.62
    braucher
    -0.59
     Agrawal
    -0.58
     Poe
    -0.58
    Демографія
    -0.58
     Ärz
    -0.58
     Smo
    -0.58
     MotionEvent
    -0.56
     préc
    -0.56
    glEnd
    -0.56
    POSITIVE LOGITS
     Assistant
    2.52
     assistant
    2.49
    Assistant
    2.41
    assistant
    2.13
     ASSISTANT
    2.11
     assistants
    1.78
     Assistants
    1.59
     Asst
    1.59
     Associate
    1.52
    Associate
    1.47
    Act Density 0.083%

    No Known Activations