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

    Neuronpedia

    INDEX
    Explanations

    a specific formatting indicator or special character

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Limoges
    -0.68
    ductory
    -0.60
    etragen
    -0.60
     extrait
    -0.60
    idiary
    -0.59
     QM
    -0.58
    hidupan
    -0.57
     cytok
    -0.57
     Wojciech
    -0.57
    Ligações
    -0.56
    POSITIVE LOGITS
     ModelExpression
    0.74
    istoitu
    0.70
     GenerationType
    0.67
    fficients
    0.64
    }))
    0.62
    énario
    0.60
    AddHtmlAttribute
    0.60
     تضيفلها
    0.60
    μβρίου
    0.59
     '\\;'
    0.59
    Act Density 0.000%

    No Known Activations