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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     varandra
    -0.84
     âmes
    -0.81
     autorytatywna
    -0.73
     stället
    -0.70
     cauza
    -0.65
     Audiodateien
    -0.64
     détaillé
    -0.63
     navideños
    -0.61
    IBOutlet
    -0.61
     الرياضيه
    -0.60
    POSITIVE LOGITS
     Seeder
    0.63
     "..\..\
    0.61
     himself
    0.58
     Vikipedi
    0.52
     Савезне
    0.51
     cherchés
    0.51
     inters
    0.51
    исленность
    0.51
     Exactos
    0.49
     "..\..\..\
    0.49
    Act Density 0.151%

    No Known Activations