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

    Neuronpedia

    INDEX
    Explanations

    terms related to social roles and hierarchies, particularly in the context of slavery and communal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.84
     Monfieur
    -0.77
     purpoſe
    -0.75
     doInBackground
    -0.74
     onCreateView
    -0.72
     mergeFrom
    -0.71
     Protestantism
    -0.70
     myſelf
    -0.69
     ſche
    -0.69
     himſelf
    -0.69
    POSITIVE LOGITS
     who
    0.98
     kteří
    0.88
     którzy
    0.84
     ktorí
    0.81
     themselves
    0.79
     folks
    0.79
     professionals
    0.75
     quienes
    0.74
    who
    0.72
     ambao
    0.72
    Act Density 0.630%

    No Known Activations