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

    Neuronpedia

    INDEX
    Explanations

    references to specific roles, professions, or titles of groups and individuals

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

    professions and their groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalTable
    -0.52
     defStyleAttr
    -0.43
    \"></
    -0.43
    UrlResolution
    -0.41
    ()},
    -0.40
     Мексичка
    -0.40
    ()}}
    -0.39
    )•
    -0.39
    OpenHelper
    -0.39
    ")}
    -0.38
    POSITIVE LOGITS
     Breeders
    0.54
     Peoples
    0.54
     Childs
    0.54
    Mothers
    0.53
     Artists
    0.53
     Poets
    0.52
     pattes
    0.52
     Mothers
    0.51
     Teachers
    0.51
     Ladies
    0.51
    Act Density 0.065%

    No Known Activations