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

    Neuronpedia

    INDEX
    Explanations

    titles, roles, and positions held by individuals in academic and professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     assistant
    -0.20
     Assistant
    -0.17
    Ñīи
    -0.17
    Assistant
    -0.17
     assistants
    -0.17
    olver
    -0.15
    assistant
    -0.15
    ueblo
    -0.14
     young
    -0.14
    ابÙĬ
    -0.14
    POSITIVE LOGITS
     Emer
    0.40
    Emer
    0.32
    emer
    0.28
     em
    0.26
     retired
    0.25
     Professor
    0.20
     Hon
    0.20
    Hon
    0.20
     knight
    0.20
     Vis
    0.20
    Act Density 0.118%

    No Known Activations