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

    Neuronpedia

    INDEX
    Explanations

    references to political positions and roles within organizations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    riwal
    -0.59
    Pab
    -0.55
    xdb
    -0.54
     بتاريخ
    -0.50
     Pioneers
    -0.50
     asiatique
    -0.49
    anía
    -0.48
     فريبيس
    -0.48
     Prehistoric
    -0.47
     possível
    -0.47
    POSITIVE LOGITS
    NameInMap
    0.92
    المناصب
    0.87
     roles
    0.84
     role
    0.83
     position
    0.80
    sidemargin
    0.78
    Geplaatst
    0.76
     positions
    0.76
     rôle
    0.73
     rôles
    0.73
    Act Density 0.064%

    No Known Activations