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

    Neuronpedia

    INDEX
    Explanations

    references to significant numbers and demographics related to events or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "another" or a number

    np_acts-logits-general · gemini-2.0-flash

    people with roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Viceroy
    -0.64
     محفوظة
    -0.61
    +#+#
    -0.59
     vœ
    -0.57
    неопр
    -0.57
     capilar
    -0.57
     AllAfrica
    -0.55
     Walkover
    -0.54
     Anfitrión
    -0.54
     nessuno
    -0.54
    POSITIVE LOGITS
     former
    0.62
     retired
    0.60
     female
    0.59
     senior
    0.58
     male
    0.56
     seasoned
    0.55
     fellow
    0.55
     graduate
    0.55
     young
    0.55
     who
    0.53
    Act Density 0.349%

    No Known Activations