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

    Neuronpedia

    INDEX
    Explanations

    questions about the degree or likelihood of a condition or process

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     estimés
    -0.70
     bool
    -0.68
    urlpatterns
    -0.65
     question
    -0.63
    bool
    -0.63
     Regardless
    -0.62
     Yes
    -0.61
    Regardless
    -0.61
    unnitel
    -0.61
    IsContent
    -0.59
    POSITIVE LOGITS
     Normdatei
    0.79
     consultato
    0.57
     Процитовано
    0.57
    Personendaten
    0.56
    ък
    0.52
     tran
    0.51
    enschappelijke
    0.50
     TextInputType
    0.50
    йтесь
    0.48
     rhestr
    0.47
    Act Density 0.041%

    No Known Activations